Page 1 of 150

(ANNA UNIVERSITY - CHENNAI)

(2021-2022)

SYLLABUS
BA4206 - BUSINESS ANALYTICS
COURSE OBJECTIVES:
Learn to
1. Use business analytics for decision making
2. To apply the appropriate analytics and generate solutions
3. Model and analyse the business situation using analytics.

UNIT I INTRODUCTION TO BUSINESS ANALYTICS (BA) (9 PERIODS)

Business Analytics - Terminologies, Process, Importance,
Relationship with Organisational Decision Making, BA for
Competitive Advantage.

UNIT II MANAGING RESOURCES FOR BUSINESS ANALYTICS (9 PERIODS)

Managing BA Personnel, Data and Technology. Organisational Structures
aligning BA. Managing Information policy, data quality and change in BA.

UNIT III DESCRIPTIVE ANALYTICS (9 PERIODS)

Introduction to Descriptive analytics - Visualising and Exploring Data -
Descriptive Statistics - Sampling and Estimation - Probability Distribution for
Descriptive Analytics - Analysis of Descriptive analytics

Page 1 of 150
 Page 2 of 150

UNIT IV PREDICTIVE ANALYTICS (9 PERIODS)

Introduction to Predictive analytics - Logic and Data Driven Models -
Predictive Analysis Modeling and procedure - Data Mining for Predictive
analytics. Analysis of Predictive analytics

UNIT V PRESCRITIVE ANALYTICS (9 PERIODS)

Introduction to Prescriptive analytics - Prescriptive Modeling - Non Linear
Optimisation - Demonstrating Business Performance Improvement.
TOTAL: 45 PERIODS
COURSE OUTCOMES:
1. Ability to understand the role of Business Analytics in decision making
2. Ability to identify the appropriate tool for the analytics scenario
3. Ability to apply the descriptive analytics tools and generate solutions
4. Understanding of Predictive Analytics and applications
5. Knowledge of Prescriptive Analytics and demonstrating business
process improvement

REFERENCES
1. Marc J. Schniederjans, Dara G. Schniederjans and Christopher M.
Starkey, " Business Analytics Principles, Concepts, and Applications -
What, Why, and How" , Pearson Ed, 2014
2. Christian Albright S and Wayne L. Winston, "Business Analytics - Data
Analysis and Decision Making" , Fifth edition, Cengage Learning, 2015.
3. James R. Evans, "Business Analytics - Methods, Models and Decisions",
Pearson Ed, 2012.

===============================================================

Page 2 of 150
 Page 3 of 150

INDEX
SL DESCRIPTION OF LESSON TOPICS PAGE No.
No.
What is business analytics?
What are the concepts of business
analytics? What are the components of
data analytics?
TERMINOLOGIES IN BUSINESS ANALYTICS
ANALYTICS TERMS
DEFINITIONS FOR THE TECHNOLOGIES AND FEATURES USED IN
ANALYTICS.
DATA CONCEPTS
HIGH-LEVEL PRACTICES AND METHODOLOGIES USED
WITH DATA.
DATA TEAM
ROLES OF THOSE COMMONLY INCLUDED IN A DATA PROJECT’S
TEAM.
RI TERMS
DEFINITIONS FOR TERMS AND CONCEPTS USED
AT RECONINSIGHT.
RI360
FEATURES UNIQUE TO RECONINSIGHT’S BUSINESS
ANALYTICS SOFTWARE, RI360.
What are the three main components of business analytics?
What is business analytics why it is required?
What are the key components of an analytics model?
What are the core areas of modern analytics?
Business analytics (BA)
Examples of Business Analytics Application
BASIC DOMAINS WITHIN ANALYTICS
Mathematical Models

Page 3 of 150
 Page 4 of 150

KEYWORDS IN BUSINESS ANALYTICS

CHALLENGES IN BUSINESS ANALYTICS

What is the importance of analytics?

What are three reasons why we study business
analytics? What is business analytics in simple
words?
12 REASONS WHY BUSINESS ANALYTICS IS IMPORTANT IN
DIGITAL AGE

Business Analytics techniques

THE PROCESS OF BUSINESS ANALYTICS
7-steps Process outlined below;

How does business analytics help in decision-making?

Business analytics help organizations to reduce risks.
The Typical Ways In Which Business Analytics Has Been Used
BUSINESS ANALYTICS TOOLS
PROBLEM SOLVING WITH ANALYTICS (To support
Organizational
Decision Making)
HOW TO DO AN ANALYTICS PROJECT
CRISP-DM REFERENCE MODEL

BUSINESS ANALYTICS FOR COMPETITIVE ADVANTAGE.

Business Analytics processed in the following five
sources for competitive advantage.
SOFTWARE SUPPORT IN BUSINESS ANALYTICS

BUSINESS ANALYTICS USED IN HUMAN RESOURCE.

What is HR
analytics? Using
data in HR

Page 4 of 150
 Page 5 of 150
How HR analytics helps Human Resource Management

Page 5 of 150
 Page 6 of 150

How to get started with HR analytics

How does HR analytics shape the business?

Organisational Structures aligning Business Analytics

MANAGING INFORMATION POLICY

What is an information management policy?
An effective information management policy will usually
include the following:
Interaction with other policies and procedures
Key aspects of an information management
policy Scope
Policy statement
Legislation and other key mandates
Creation and management of information assets
Chief Information Governance Officer (CIGO): -
information management environment
Senior management
Information management unit
ICT staff: responsible for maintaining the technology for [the
agency's] business information systems.
Agency security advisor:
Managers and
supervisors Contract
staff: Communication
and training Monitoring
and review
Resources - that give extra information
Senior management endorsement

WHAT IS DATA QUALITY AND MASTER DATA MANAGEMENT?

EXAMPLES OF DATA SOURCES AND USES

Page 6 of 150
 Page 7 of 150
WHAT IS BIG DATA

Page 7 of 150
 Page 8 of 150

DATA SETS AND DATABASES

TYPES OF DATA
MEASUREMENT SCALES
Operations have meaning
DATA RELIABILITY AND VALIDITY
Examples:
DATA QUALITY
Rules for evaluating data quality:
WHY DATA QUALITY AND MASTER DATA MANAGEMENT
ARE IMPORTANT
Growing challenges for data quality in today’s companies:
Organization to think about how to collect reliable data:
HOW TO ACHIEVE A HIGH LEVEL OF (MASTER) DATA QUALITY
ORGANIZATION OF DATA QUALITY AND MASTER
DATA MANAGEMENT
PROCESSES FOR DATA QUALITY AND MASTER
DATA MANAGEMENT
The data quality cycle is made up of the following phases
DATA QUALITY AND MASTER DATA MANAGEMENT SOFTWARE
Software tools assist in different ways by providing:
Data quality - Providers can be classified - history in the
following
groups:
DATA QUALITY AND MASTER DATA MANAGEMENT INITIATIVES
IS THE SUCESS OF SEVERAL COMPANIES.

CHANGES MAY BE REQUIRED IN BUSINESS ANALYTICS -

THE ROLE OF BUSINESS ANALYTICS IN CHANGE MANAGEMENT
What is change management?
Change management consists of five
components: BA change management tasks
Identifying and clarifying the current state of the business
Providing current data on the state of the market
Page 8 of 150
 Page 9 of 150

Researching how proposed changes might impact the

business Collecting use cases
Defining and communicating the desired future state
Creating a comprehensive plan

UNIT III
DESCRIPTIVE ANALYTICS
What is descriptive analysis analytics?
5 EXAMPLES OF DESCRIPTIVE ANALYTICS
USING DATA TO IDENTIFY RELATIONSHIPS AND TRENDS

VISUALIZING AND EXPLORING DESCRIPTIVE DATA

How is data visualization used in descriptive
analytics? Why are visuals so important with
descriptive analytics? What is data visualization
and exploration?
Data visualization and descriptive statistics
DESCRIPTIVE STATISTICS AND DATA VISUALIZATION
Examples of Descriptive Statistics
Why is Descriptive Statistics
Important? What Are Descriptive
Statistics?

Types of Descriptive Statistics

Why do we need statistics that simply
describe data? What are mean and standard
deviation?
Data Visualization
Different Forms Of Data
Visualization Why is Data
Visualization Important?
Data Visualization and Descriptive Statistics
The Proper Tools
Page 9 of 150
 Page 10 of
PRESCRIPTIVE DECISION MODELS 150

EXAMPLE OF PRESCRIPTIVE PRICING MODEL

TYPES OF VARIABLES, DESCRIPTIVE STATISTICS, AND SAMPLE

Page 10 of
150
 Page 11 of
150
SIZE
WHAT IS A VARIABLE?
Variables can be classified into various
ways Quantitative vs qualitative
Dependent and independent variables

Descriptive Statistics
DESCRIPTIVE STATISTICS CAN BE BROADLY PUT UNDER
TWO CATEGORIES:
Summary statistics
PROBABILITY DISTRIBUTION FOR DESCRIPTIVE ANALYTICS
What is descriptive probability?
What is the purpose of descriptive statistics?
Probability - terminologies.
Bernoulli Trials
Probability Mass
Function Normal
Distribution

ANALYSIS OF DESCRIPTIVE ANALYTICS

How do you analyze descriptive analytics?
What techniques are used in descriptive analytics?
COMMON APPLICATIONS OF DESCRIPTIVE ANALYTICS:
More Use Cases of Descriptive Analytics
Descriptive Analytics: Industry Applications
The Five Steps to analyse Descriptive Analytics
Does Descriptive Analytics Have Any Disadvantage?
The Role of Descriptive Analytics in Future Data Analysis

UNIT IV
PREDICTIVE ANALYTICS
What is meant by predictive analytics?

Page 11 of
150
 Page 12 of
150
How do you develop a predictive model?
THE SIX STEPS OF THE PREDICTIVE ANALYTICS PROCESS
The process of Predictive Analytics includes the following steps
:
What can you do with Predictive Analytics?
INDUSTRIES USING PREDICTIVE ANALYTICS MODEL
Advantages of Predictive Analytics

PREDICTIVE ANALYSIS - LOGIC AND DATA DRIVEN MODELS

PREDICTIVE MODELING
Types Of Predictive Models
SOME OF THE MOST POPULAR METHODS INCLUDE
THE FOLLOWING:
Common algorithms for predictive modelling
Benefits of predictive modelling
Predictive modeling tools
The future of predictive modeling

DATA MINING FOR PREDICTIVE ANALYTICS

How do data mining and predictive analytics work?
What is the difference between data mining and predictive
analytics? Why data mining is important in predictive
analytics?
Data Mining
Data mining commonly involves the following 6 tasks
DATA MINING TECHNIQUES
PREDICTIVE ANALYTICS TECHNIQUES
APPLICATIONS OF PREDICTIVE ANALYSIS THROUGH DATA
MINING
CONCLUSIONS
Predictive analytics is the future of Data Mining

ANALYSIS OF PREDICTIVE ANALYTICS

Page 12 of
150
 Page 13 of 150

PREDICTIVE ANALYTICS IS A DECISION-MAKING TOOL IN A

VARIETY OF INDUSTRIES.
THERE ARE THREE COMMON TECHNIQUES USED IN
PREDICTIVE ANALYTICS:
PREDICTIVE ANALYTICS VS. MACHINE LEARNING
PREDICTIVE ANALYTICS - MAKES PREDICTIONS FOR THE
FUTURE PROGRESS

UNIT V
PRESCRITIVE ANALYTICS
INTRODUCTION TO PRESCRIPTIVE ANALYTICS
What Is Prescriptive Analytics?
BENEFITS OF PRESCRIPTIVE ANALYTICS
OTHER AREAS OF PRESCRIPTIVE ANALYSIS APPLICATION

PRESCRIPTIVE MODELING - PRESCRIPTIVE PROCESS MODELS

PRESCRIPTIVE PROCESS MODELS

PRESCRIPTIVE MODELING - (NON LINEAR OPTIMISATION)

WHAT IS LINEAR VS NONLINEAR?
What is the importance of nonlinear
programming? What is a non linear
optimization problem?
What is the main characteristic of a non-linear optimization
problem?
Difference Between Linear And Nonlinear Optimization
Different Prescriptive Analytics Approaches

Rules-based modeling, known as

heuristics Disadvantage of heuristics

LINEAR PROGRAMMING (OPTIMIZATION MODELING)

Benefits of optimization modeling
Page 13 of 150
 Page 14 of 150

Disadvantages of optimization modeling

Prescriptive Analytics
Software Prescriptive
Analytics Packages
Optimization Platforms
Advantages of optimization
platforms Disadvantages of
optimization platforms
Problems That Can Be Solved by Prescriptive Analytics

PRESCRITIVE ANALYTICS - BUSINESS PERFORMANCE

IMPROVEMENT - DEMONSTRATING BUSINESS PERFORMANCE
IMPROVEMENT
Role of Prescriptive Analytics in Business Decision Making
How Does Prescriptive Analytics Work In The Overall
Business Decision Process?
Types Of Prescriptive Analytics
TOOLS REQUIRED FOR PRESCRIPTIVE ANALYTICS
WHAT IS THE DIFFERENCE BETWEEN PREDICTIVE AND
PRESCRIPTIVE ANALYTICS
HOW PRESCRIPTIVE ANALYTICS BENEFITS BUSINESS
PERFORMANCE IMPROVEMENT
PRESCRIPTIVE ANALYTICS: MANAGE MANUFACTURING COSTS
AND IMPROVE ROI
Maximizing decision value
WHAT IS PRESCRIPTIVE ANALYTICS, AND WHAT CAN IT DO FOR
YOUR BUSINESS?
WHY PRESCRIPTIVE ANALYSIS MATTERS TO YOUR BUSINESS?
PRESCRIPTIVE ANALYSIS HAS BENEFITS SUCH AS:
LESSON QUESTIONS - (2 MARKS for some questions) / (15 138
Marks
for some questions)
Page 14 of 150
 Page 15 of 150

BUSINESS ANALYTICS - (BA4206)

UNIT I

INTRODUCTION TO BUSINESS ANALYTICS (BA)

(Business Analytics - Terminologies, Process, Importance, Relationship with

Organisational Decision Making, BA for Competitive Advantage).

What is business analytics?

Business analytics (BA) is a set of disciplines and technologies for solving
business problems using data analysis, statistical models and other
quantitative methods. It involves an iterative, methodical exploration of an
organization's data, with an emphasis on statistical analysis, to drive
decision-making.

What are the concepts of business analytics?

Business analytics is concerned with extracting meaningful insights from and
visualizing data to facilitate the decision-making process, whereas data science
is focused on making sense of raw data using algorithms, statistical models,
and computer programming.

What are the components of data analytics?

Key Components of Data Analytics
 Roadmap and operating model. Every organization tends to utilize
mapping tools to make sustainable designs for their processes and
capabilities. ...
 Data acquisition. ...
 Data security. ...
 Data governance and standards. ...
 Insights and analysis. ...
Page 15 of 150
 Page 16 of 150
 Data storage. ...
 Data visualization. ...

Page 16 of 150
 Page 17 of 150

 Data optimization.

(1.2) TERMINOLOGIES IN BUSINESS ANALYTICS

What is business analytics terminology?

Business Analytics is the process by which businesses use statistical
methods and technologies for analyzing historical data in order to gain new
insight and improve strategic decision-making.

ANALYTICS TERMS
DEFINITIONS FOR THE TECHNOLOGIES AND FEATURES USED IN ANALYTICS.

Dashboard is a general software application user design construct used in

many software applications to provide the user with a bird’s eye view of the
software application. In data applications, dashboards display summary
information of one or more reports in various visual arrays, such as charts,
graphs and tabular summaries. Dashboards often use data visualizations.
Data Cleansing reviews all business data to ensure it is formatted correctly
and consistently, corrects as needed, or notifies end-user to address ‘dirty’
data if it does not meet the business standards. Occurs in data processing,
step one of the data pipeline. Only clean data can move to the next step of
the data pipeline.
Data Processing / Data Processor is a software designed to extract business
data from all data sources and conduct data cleansing and transformation.
Also the first part of a business’s data pipeline. Also called: ETL (Extract,
Translate, Load).
Data Store is a data information architecture. At ReconInsight, we believe it is
an important part of a data pipeline that provides storage and security for all
business data. Also called: Data warehouse, Data warehousing.
Data Translation involves mapping and applying custom business logic to
cleansed business data with the goal of organizing and normalizing
business information for storage and consumption. Occurs after data
Page 17 of 150
 Page 18 of 150
cleansing in data processing, step one of the data pipeline. Also called:
Data transformation.

Page 18 of 150
 Page 19 of 150

Data Visualization is the science of deriving meaning from data sets by using
graphical and other non-tabular presentations. Examples of traditional data
visualizations include line series charts, pie charts, and column charts.
Research over the past decades have moved data visualization forward
rapidly with the advent of new graphical representations. Impactful data
visualization thought leaders include Edward Tufte and Stephen Few.
Database is a computer system (cloud or on-prem) that stores data in a
persistent state, typically to be retrieved and modified by other software. In
analytics, reporting and analysis software read, interpret, and display
database data.
Geospatial Analytics associates data with a location. It is a type of data
visualization that is often used to overlay data onto digital maps. The data
is represented as data points or data summaries of geographic regions.
Pivot Table summarizes information extracted from large, detailed datasets.
Multi-level pivots allow you to create hierarchies within the pivots to derive
meaning. The term ‘pivot’ comes from a numeric value ‘pivoting’ on a
discrete list. For example, the total number of cars pivoted against car
model will summarize how many cars align with each car model. Pivot table
data can be displayed as a table, pie chart, bar chart, or column chart.
Time-Series Forecasting applies statistical modeling to a time-series and
forecasts that into future time periods.
Trends typically refer to a time-series data trend. Time-series trends
address the change of a data value through multiple time periods.
User Interface represents any visual interface that a user of a technology
interacts with during use. At ReconInsight we also use this to describe the
last part of a data pipeline, which is often represented by a data analytics
software.

DATA CONCEPTS
HIGH-LEVEL PRACTICES AND METHODOLOGIES USED WITH DATA.

Artificial Intelligence (AI) is a broad term for using vast data sets to provide a
Page 19 of 150
 Page 20 of 150
high level of understanding and sometimes a higher level of consciousness.
Within the realm of analytics, artificial intelligence can apply to machine
learning.

Page 20 of 150
 Page 21 of 150

Big Data is a widely-used term referring to the derivation of insights from

large data sets. Big data is often associated with large unstructured data
sets such as social media feeds and IoT data streams. “Big Data” is often
overused and misused for the purposes of marketing.
Business Analytics (BA) involves analyzing business data to effect change at
a company. It is process-oriented and focused on using data as a functional,
decision making tool to improve business efficiencies, business operations,
and business profits. Business Intelligence (BI) describes the act of informing
an organization using data.
Business intelligence is typically associated with information dashboarding,
specifically high-level reporting that summarizes previous traditional
tabular reporting into charts and data visualizations. In recent years,
business intelligence has been overcome by business analytics because
users are asking deeper questions of their data.
Business Management encompasses all operations necessary to run an
organization. Business management requires standardized processes to
effectively operate all departments. Technologies for data pipelines and
data analytics can greatly enhance
the ease and efficacy of an organization’s business management efforts.
Data Analytics is the reporting and visualization of business information. A
more technical definition would include: the process of cleansing,
transforming, and modeling data with the goal of discovering useful
information, informing conclusions and supporting decision-making.
Data Science is the act of applying industry domain knowledge and advanced
statistical analysis to one or more data sets. It includes bringing together
data from various sources, applying statistical analysis, and presenting the
results to key decision makers. Data science tools include statistics models,
machine learning, artificial intelligence, and data visualization.
Database Management is the act of maintaining complex databases.
Databases are computer application systems that require software patches,
backups, storage management, performance tuning, and software patches.
Descriptive Analytics explains the current state of the data. It is the first of
Page 21 of 150
 Page 22 of 150
three stages in the progression of increased sophistication in data
analytics. Descriptive Analytics is followed by predictive analytics and
prescriptive analytics. Descriptive analytics explains the current state of the
data. Predictive analytics applies statistical

Page 22 of 150
 Page 23 of 150

analysis to predict future behavior. Prescriptive analytics provides a specific

action plan to improve a business function.
Information Repository refers to a data set that is organized for decision
making. "Decisions are made on information, not data.” An information
repository can be comprised of one or more databases, documents, or any
other electronic data system. Predictive Analytics applies statistical analysis
to predict future behavior. explains the current state of the data. It is the
second of three stages in the progression of increased sophistication in data
analysis. Predictive Analytics is preceded by descriptive analytics and
followed by prescriptive analytics. Related to: Time-Series Forecasting.
Prescriptive Analytics is finding the best course of action for a given situation.
It is the third of three stages in the progression of increased sophistication in
data analysis.
Prescriptive analytics is preceded by descriptive analytics and prescriptive
analytics. Statistical Analysis is the general application of math and
statistics to data. It is used in data science, time-series forecasting,
predictive analytics.
Variety, Velocity, Volume are often used to describe large data sets used in
data analytics. Volume describes the vast amount of data that often feeds
into analysis. Velocity describes how quickly the data sets change. Variety
describes how many types of data are used for analysis.

DATA TEAM
ROLES OF THOSE COMMONLY INCLUDED IN A DATA PROJECT’S TEAM.

Business Analysts analyze an organization's data, processes, and systems to

provide guidance for improving business processes, products, services and
software through data analysis. Often a member of a data team.
Business Expert is an employee with in-depth domain knowledge of how a
business operates, the systems it uses, internal and external processes,
company structure and strategies, and technologies. At ReconInsight, we
recommend a Business Expert be a part of a company's data team.
Page 23 of 150
 Page 24 of 150
Data Analyst is a technical role focused on implementing, supporting, and
optimizing data analytics technology. They are skilled administrators,
architects, and users of data tools.

Page 24 of 150
 Page 25 of 150

RI TERMS
DEFINITIONS FOR TERMS AND CONCEPTS USED AT RECONINSIGHT.
Data Master is used to describe members of the ReconInsight data team. Our
data masters are seasoned information professional that understand data
from soup to nuts. Data Masters have the unique ability to work with both
business users and technical users. They work directly with clients to
understand business needs, model data, and implement a world class data
pipeline using Ri360 technology.

RI360
FEATURES UNIQUE TO RECONINSIGHT’S BUSINESS ANALYTICS
SOFTWARE, RI360.
Collector is an Ri360-specific technology feature that stores data for a
specific business purpose. For example, an Ri360 collector can store all sales
transactions, a financial system’s general ledger, or all shipments. Ri360
automatically builds the data storage using a meta-data definition. Ri360
collector data processing is developed that ensures the collector contains up-
to-date information. Ri360’s user interface provides an automated data
exploration interface. Ri360 allows users to create information dashboards
using collector data. A single Ri360 collector, coupled with the Ri360 user
interface, can provide/replace dozens of traditional reports.
Collector Datasheet is the tabular representation of data stored in an Ri360
collector snapshot.
Collector Snapshot is a single instance of an Ri360 Collector. A single
instance may represent all the data for a time period. Snapshots are
created regularly and automatically over time. This consistency and
repetition provides a steady and reliable decision making platform.
Data Levels are an Ri360-specific technology feature that represent
cardinality relationships within an Ri360 Collector Datasheet. A single data
level can be represented in a single tabular view. When a datasheet
Page 25 of 150
 Page 26 of 150
contains one or more parent- child relationships, multiple data levels are
necessary to represent the business data.

Page 26 of 150
 Page 27 of 150

Data levels enable users to easily drill into the details of objects with
parent-child relationships.
=================================================================
What are the three main components of business analytics?
There are three types of analytics that businesses use to drive their
decision making; descriptive analytics, which tell us what has already
happened; predictive analytics, which show us what could happen, and
finally, prescriptive analytics, which inform us what should happen in the
future.
(1) Descriptive Analytics
is the examination of data or content, usually manually performed, to
answer the question “What happened?” (or What is happening?),
characterized by traditional business intelligence (BI) and visualizations such
as pie charts, bar charts, line graphs, tables, or generated narratives.
(2) Predictive analytics
is a branch of advanced analytics that makes predictions about future
outcomes using historical data combined with statistical modeling, data mining
techniques and machine learning. Companies employ predictive analytics to
find patterns in this data to identify risks and opportunities.
(3) Prescriptive Analytics
is a form of advanced analytics which examines data or content to answer
the question “What should be done?” or “What can we do to make
happen?”, and is characterized by techniques such as graph analysis,
simulation, complex event processing, neural networks, recommendation
engines.

What is business analytics why it is required?

Business analytics also allows organizations to automate their entire
decision- making process, so as to deliver real-time responses when needed.
One of the apparent importance of business analytics is the fact that it
helps to gain essential business insights. It does this by presenting the
right data to work it.
Page 27 of 150
 Page 28 of 150

What are the key components of an analytics model?

This article will discuss 4 main components of an analytics model, namely:

Page 28 of 150
 Page 29 of 150

1) Data Component,
2) Algorithm Component,
3) Real World Component, and
4) Ethical Component. Knowledge from data science training courses is
necessary for acquiring skills in Components 1 and 2 (Data Component and
Algorithm Component).

What are the core areas of modern analytics?

In the closing keynote at Data Summit 2019, Radiant Advisers' John O'Brien
identified four focus areas for data analytics—
understanding customer behavior,
understanding product usage,
increasing operational efficiency, and
business model innovation.

Business analytics (BA)

refers to the skills, technologies, and practices for continuous iterative exploration
and investigation of past business performance to gain insight and drive business
planning. Business analytics focuses on developing new insights and
understanding of business performance based on data and statistical methods. In
contrast, business
intelligence traditionally focuses on using a consistent set of metrics to
both measure past performance and guide business planning. In other
words, business
intelligence focusses on description, while business analytics focusses on
prediction and prescription

Business analytics
makes extensive use of analytical modeling and numerical analysis,
including explanatory and predictive modeling,[2] and fact-based
management to drive decision making. It is therefore closely related to
management science. Analytics may be used as input for human decisions
Page 29 of 150
 Page 30 of 150
or may drive fully automated decisions. Business intelligence is querying,
reporting, online analytical processing (OLAP), and "alerts."
In other words, querying, reporting, and OLAP are alert tools that can answer
questions such as what happened, how many, how often, where the problem
is, and what actions

Page 30 of 150
 Page 31 of 150

are needed. Business analytics can answer questions like why is this
happening, what if these trends continue, what will happen next (predict),
and what is the best outcome that can happen (optimize)

Examples of Business Analytics Application

In healthcare, business analysis can be used to operate and manage clinical
information systems. It can transform medical data from a bewildering array
of analytical methods into useful information. Data analysis can also be used
to generate contemporary reporting systems which include the patient's
latest key indicators, historical trends and reference values.
 Decision analytics: supports human decisions with visual analytics
that the user models to reflect reasoning.[5]
 Descriptive analytics: gains insight from historical data with
reporting, scorecards, clustering etc.
 Predictive analytics: employs predictive modelling using statistical
and machine learning techniques
 Prescriptive analytics: recommends decisions using optimization, simulation,
etc.

BASIC DOMAINS WITHIN ANALYTICS

 Behavioral analytics
 Cohort analysis
 Competitor analysis
 Cyber analytics
 Enterprise optimization
 Financial services analytics
 Fraud analytics
 Health care analytics
 Key Performance Indicators (KPI's)
 Marketing analytics
 Pricing analytics
 Retail sales analytics

Page 31 of 150
 Page 32 of 150
 Risk & Credit analytics

Page 32 of 150
 Page 33 of 150

 Supply chain analytics

 Talent analytics
 Telecommunications
 Transportation analytics
 Customer Journey Analytics
 Market Basket Analysis

Mathematical Models
•Hypothesis Testing
•Correlation, Regression, Forecasting
•Sampling
•Queueing Theory and Simulation
•Linear Programming
•Network Optimization
•Dynamic Programming
•Nonlinear Optimization
•Game Theory
•Decision Trees
•System Dynamics
•Markov Chains and Hidden Markov Models
•Bayesian Statistics

Keywords
Business Intelligence (BI):
Business Intelligence (BI) is a set of theories, methodologies, processes,
architectures, and technologies that transform raw data into meaningful
and useful information for business purposes.
1. Data Extraction:
Data extraction is the act or process of retrieving data out of (usually
unstructured or poorly structured) data sources for further data
processing or data storage (data migration).
2. Data Mining (DM):
Page 33 of 150
 Page 34 of 150

Data mining (the analysis step of the “Knowledge Discovery in Databases”

process, or KDD), an interdisciplinary subfield of computer science, is the
computational process
of discovering patterns in large data sets involving methods at the
intersection of artificial
intelligence, machine learning, statistics, and database systems.
3. Data Warehousing:
In computing, a data warehouse or enterprise data warehouse
(DW, DWH, or EDW) is a database used for reporting and data
analysis.
4. Decision Support Systems (DSS):
A decision support system (DSS) is a computer program
application that analyses business data and presents it so that users can
make business decisions
more easily.

CHALLENGES
Business analytics depends on sufficient volumes of high-quality data.
The difficulty in ensuring data quality is integrating and reconciling data across
different systems, and then deciding what subsets of data to make available.[3]
Previously, analytics was considered a type of after-the-fact method
of forecasting consumer behavior by examining the number of units sold in
the last quarter or the last year.
This type of data warehousing required a lot more storage space than it did
speed. Now business analytics is becoming a tool that can influence the
outcome of customer interactions.
When a specific customer type is considering a purchase, an analytics-
enabled enterprise can modify the sales pitch to appeal to that consumer.
This means the storage space for all that data must react extremely fast to
provide the necessary data in real-time.
================================================================

Page 34 of 150
 Page 35 of 150

(1.2) BUSINESS ANALYTICS - IMPORTANCE

What is the importance of analytics?

Data analytics is important because it helps businesses optimize their
performances. Implementing it into the business model means companies
can help reduce costs by identifying more efficient ways of doing business
and by storing large amounts of data.

What are three reasons why we study business analytics?

Analytics help in making informed business decisions. It brings agility to a
business. Again, machines or technology alone cannot make business
decisions. You need human brains with adept knowledge and skill sets to
make things work in favour of your business.

What is business analytics in simple words?

Specifically, business analytics refers to: Taking in and processing historical
business data. Analyzing that data to identify trends, patterns, and root
causes. Making data-driven business decisions based on those insights.

12 REASONS WHY BUSINESS ANALYTICS IS IMPORTANT IN DIGITAL AGE

By now, we are sure you might have a brief idea of what business analytics
is, how it works and why it is the next big thing on the market.
As the title suggests, we will focus on why business analytics plays such a
vital role in the growth of businesses. Lets get started.
1. Enhance Customer Experience
With the variety of options available, customers are spoiled for choice. To
ensure businesses can retain their customer base, they turn to analytics.
For example, companies can analyse a customers interaction on their
website and past purchasing habits. Based on this data, they can analyse
patterns and make improvements to their website performance. This can
be as simple as sending a push notification prompting products that
customers have added to their shopping cart. This will result in overall
Page 35 of 150
 Page 36 of 150
better customer experience, and eventually, loyalty.

Page 36 of 150
 Page 37 of 150

2. Make Informed Decisions

Businesses often outsource a few of their processes to enhance their
efficiency. When it comes to selecting vendors for such activities, they need
to know which one will bring more profits. Analytics can help them evaluate
supplier performance based on customer ratings, order fulfilment speed,
quality, etc. This data will help them decide which one works best for their
business.
3. Reduce Employee Turnover
Every year, companies have to bear an extensive cost due to employee
onboarding and attrition. To save time and costs, HR professionals can use
analytics tools to examine the likelihood of an employee aligning with a
companys culture, tracking their performance and how satisfied they are
with the new role, and similar factors. Once you know such answers, it will be
easier to recognise employees who will stick to your company for a long
time.

4. Improve Efficiency
Efficiency is not always limited to employees. Businesses can also analyse
other resources to learn more about their performance. For example, a
grocery store chain was able to reduce refrigeration costs by merely
analysing the temperatures of in-store coolers. It was found that the
refrigerators were being kept several degrees lower than necessary, which
increased power usage. So, by increasing the temperature, power costs
went down without affecting safe food storage. Business owners can learn
from such examples and use data to make their resources efficient.
5. Identify Frauds
Finance companies have begun using analytics to reduce fraud. One way
they do this is by using data to identify potentially fraudulent purchases,
based on the analysis of customers previous transactions. These companies
also use predictive analytics to look at customer profiles and gauge the level
of risk. This helps rate the risk that a particular customer presents and use
this analysis to prevent losses, and builds stronger customer relationships.
Page 37 of 150
 Page 38 of 150
6. Cut Manufacturing Costs
One company that has outranked everyone when it comes to using analytics to
reduce manufacturing costs is Intel. Initially, this tech giant would perform 19,000
tests on each

Page 38 of 150
 Page 39 of 150

chip being manufactured. With the advent of predictive analysis, Intel was
able to determine which chips need, which tests before their launch. By
using the data collected from all of that testing, it has been able to save
almost $3 million.

7. Make The Most Of Your Investment

Earlier, business people would rely on traditional marketing techniques to
gain and retain customers. However, the internet has changed this
completely. Now search marketing has become the most efficient and
inexpensive way for businesses to find leads. By using business
intelligence, marketers can craft perfect campaigns and strategies,
eventually increasing chances of higher ROI.
8. Improved Advertising
Advertising is expensive; hence marketers must know how to get the best
return on investment. This is why they use analytical methods such as A/B
and C split-testing. When it comes to advertising online, all landing pages,
pop-ups, and even product descriptions are evaluated and tweaked to
ensure maximum results. Even the way products are positioned on the
website is assessed to identify the best location to drive more engagement
and sales.
9. Better Product Management
When it comes to retail companies, they have more than a thousand
products to offer. So, how do they decide which ones to release at which
time? Yes, the answer is data analytics. Such businesses analyse which are
the most popular products depending on the region and season. This data is
then used to target the right product at the right time, which eventually has
a positive impact on sales.
10. Tackle Problems
Whenever a problem arises, a business often pauses the current
operations, which leads to a huge loss. To prevent such situations, business
analysts help the organization to make an informed decision by providing
information that can help identify potential risks and avoid any occurrence
Page 39 of 150
 Page 40 of 150
of loss. These professionals can use the raw data to detect a malfunction in
the existing system, and thus help business owners to fix it at the earliest.
11. Accelerate Through Uncertainty

Page 40 of 150
 Page 41 of 150

Look at the current business scenario. Owing to the lockdown across the
globe, the business environment is as uncertain as it gets. Almost nobody
has an idea when things will get back to normal, and the corporate world will
be allowed to resume its operations. At such times, data analytics can be
used to resolve supply chain issues, introduce crisis management solutions,
optimize costs, and more.
12. Conduct A Competitor Analysis
Today, almost every business has a clear idea of its competitors. An
effective way to get ahead of them is by understanding what they are up
to, their strategies, USPs, etc. By gathering this data by conducting a SWOT
analysis, you can get a preview of how your business is performing as
compared to your competitors.
=================================================
================
(1.3) THE PROCESS OF BUSINESS ANALYTICS

Business Analytics techniques can be deployed in any industry where data is

conquered and handy to obtain business solutions through concerned data
and curve it into understanding and knowledge to make valuable decisions.
Multiple BI tools are implemented that helps an organization to obtain a
competing asset in the market.

THE PROCESS OF BUSINESS ANALYTICS

7- steps Process outlined below;

Step 1: Address the Business Problems

Initially, business problems need to be addressed, the purpose of applying
analytics is sometimes designated categorically or broken into parts. So, relevant
data is selected to address these business problems by business users or business
analysts equipped with domain knowledge.
Some examples are: keeping modeling for a postpaid subscription,
fraud detection for credit cards, or customer analysis of a mortgage

Page 41 of 150
 Page 42 of 150
portfolio. Business experts define perimeters for the analytical process
which is crucial for assuring general understanding of the goal.
Step 2: Identify Potential Interest from Data

Page 42 of 150
 Page 43 of 150

All sources of data having potential interest are required to identify. The key
asset in this step is the more the data, the better it is. All the data will then
be accumulated and consolidated in a data warehouse or data mart or at a
spreadsheet file. Some exploratory data analysis is executed to do the
computation for missing data, removing outliers, and transforming variables.
For example, time-series analysis graphs are plotted to figure out
some patterns or outliers, scatter plots are used to find correlation or non-
linearity, OLAP system for multidimensional analysis.
Step 3: Inspect the data
Once moving to the analytics step, an analytical model will be predicted on
the prepared and transformed data using statistical analysis techniques like
correlation analysis
and hypothesis testing. The analyst figures out all parameters in connection
with the target variable. The business expert also performs regression
analysis to make simple predictions depending upon the business objective.
In this step, data is also often reduced, divided, crumbled and compared
with various groups to derive powerful insights from data.

Step 4: Interpretation and Evaluation by Experts

Finally, after obtaining model results, business experts interpret and
evaluate them. Results may be clusters, rules, relations, or trends known as
analytical models derived from applying analytics. Experts use predictive
techniques like decision trees, neural networks, logistics regression to
reveal the patterns and insights that show the relationship and invisible
indication of the most persuasive variables.
Several prediction models are executed to select the best performing
Page 43 of 150
 Page 44 of 150
model on the basis of model accuracy and consequences. But yet, to
explore unknown though

Page 44 of 150
 Page 45 of 150

engaging and tribal patterns are challenging that can add value to data and
convert into new turnout opportunities.
Step 5: Optimization of Best Possible Solution
Once the analytical model has been validated and approved, the analyst
will apply predictive model coefficients and conclusions to drive “what-if”
conditions, using the defined to optimize the best solution within the given
limitations and constraints.
Necessary considerations are how to serve model output in a user-friendly
way, how to integrate it, how to confirm the monitoring of the analytical
model accurately. An optimal solution is chosen based on the lowest error,
management objectives, and identification of model coefficients that are
associated with the company’s goals.
Step 6: Decision Making and Estimate conclusions
Analysts then would make decisions and endure action based on the
conclusions derived from the model in accordance with the predefined
business problems. Spam of period is accounted for the estimation of
conclusion, all the favorable and opponent consequences are measured in
this duration to satisfy the business needs.
Step 7: Upgrade performance system
At last, the outcome of decision, action and the conclusion conducted from
the model are documented and updated into the database. This helps in
changing and upgrading the performance of the existing system.
Some queries are updated in the database such as “ were the decision and
action impactful?” “ what was the return or investment ?”,”how was the
analysis group compared with the regulating class?”. The performance-
based database is continuously updated once the new insight or knowledge
is extracted.

Conclusion - Business analytics can result in powerful and valuable visions

that would not be feasible in the truancy of data. With implementing
analytics, one can increase the operational efficiencies of any business over
a range of functions. In essence, to assure the adaptation of the
Page 45 of 150
 Page 46 of 150
recommendations that are brought out from data, one can interpret
organizational behavior shifts in a way that provides the forecasted benefit.
=================================================
=================

Page 46 of 150
 Page 47 of 150

(1.4) HOW DOES BUSINESS ANALYTICS HELP IN DECISION-MAKING?

How does business analytics help in decision-

making? Better business decisions
Data analytics allows Executives to make decisions based on statistical facts.
Those facts can be used to guide choices about future company growth by
evaluating a long-term view of the market and competition.

Business analytics help organizations to reduce risks.

By helping them make the right decisions based on available data such as
customer preferences, trends, and so on, it can help businesses to curtail short
and long-term risk.

How Business Analytics impacts Decision Making in Businesses

Business analytics enables managers to understand their company's
dynamics, forecast market developments, and manage risks.
Companies are adopting analytics and rigorous statistical reasoning to make
decisions
that enhance efficiency, risk management, and profits, rather than “going with
gut” when keeping inventories, pricing solutions, or employing people.
Data is provided for all essential company activities, including industry
trends, consumer behavior, productivity, inventory, and thorough financial
analysis.
Business intelligence software collects information and transforms it into
clear insights to enable actionable and strategic decision-making, allowing
employees to easily achieve their objectives.

When we say that business analytics assists with decision-making,

we mean that it gives information that can help the firm decide the route it
will go in the future.
Increasing bottom line and profitability, offering stronger and more
sustainable risk management, and decreasing total expenses — including

Page 47 of 150
 Page 48 of 150
overheads, when possible — are some of the typical ways in which business
analytics has been used thus far.

Page 48 of 150
 Page 49 of 150

1. By analyzing consumer trends, we can provide unique

customer experiences
Data analytics is becoming an essential component of the foundation that
all organizations must build if they are to prosper. When contextualized
more excellently through a business-specific lens, it gives a particular depth
that can assist the organization make sense of how consumers are
consuming its products or services. What is a realistic example of this in
action in a real-world setting? A telecom business can use analytical
models, especially predictive models, to ensure that their consumers stay
with them for a longer period of time and to evaluate the effectiveness of
their marketing activities.
Similarly, an online eCommerce company may use business analytics data to
determine which of their visitors stay and for how long, as well as which
of them return – and
why.
Questions of this kind can help to build a comprehensive platform or
foundation upon which a strong plan can be implemented.
And the greatest thing is that it can be altered as additional data is
collected, so it's never too late to make a course correction that may
totally impact an organization's destiny!
Thus, the business analysis provides an organization with the proper data to
acquire a competitive edge and ensure that they can cater to their
consumers in the best possible way, for the best possible conclusion.

2. Significantly increasing service metrics performance

Business analytics has several applications and benefits, and it would be
imprudent to focus just on one element when there are others that can also
be useful.
Consider business analytics to be a tree, with roots that go deep into the
structural machinery of the organization and branches that touch every
area of the organization. Whatever function or application you can think of,
there is a possibility that business analytics may have a beneficial influence
Page 49 of 150
 Page 50 of 150
on it, and not only that, but it can also alter it for the better.

Page 50 of 150
 Page 51 of 150

Consider internal resource management as an example. Business analytics

may give critical insight into how to manage expenses, where a certain cost
can be restructured so that it does not affect the bottom line, and so on.
Furthermore, an organization can conduct an in-depth analysis of firm
performance in terms of particular critical performance indicators (these
depend on the nature of the organization for the most part).
Then, business analytics may shed light on workers' real performance and
show how they might be better managed, such as which variables affect
their motivation, how long they are likely to stay in an organization, and so
on.
Finally, it has the potential to significantly alter an organization's approach to
its people - the fundamental driving force behind its growth.
Taking into consideration numerous data points such as professional
performance, experience, age, and a number of other characteristics, it
becomes easier to make educated estimates about the performance of
present and prospective workers. There will also be information into who is
most likely to perform to their full potential in which job.
To summarise, once the insight from business analytics is utilized, there will
be a significant increase in the company's overall performance

3. Providing insight into risk management and how to improve

Page 51 of 150
 Page 52 of 150
overall management

Page 52 of 150
 Page 53 of 150

Understanding risk is a critical component of optimizing company choices,

and business analytics excel at effectively resolving this issue. Business
analytics may be used to analyze all of an organization's data, whether it is
housed in databases or is unstructured and spread across several sources.
Business analytics may be used to avoid crises or optimize reactions during
a crisis period in order to resolve it in the best way possible by providing
insight into what is likely to happen. This translates into better risk
management, but in the context of the organization's work processes, it
translates into overall better management practices. How does this manifest
itself in practice? For one thing, banks may use it to get a better image of
who they should lend to by analyzing a potential client's credit ratings and
customer loyalty rating.
Furthermore, the business analyst may be used to determine if some high-
risk payments are actually worth the risk, or whether particular delinquents
on the credit spectrum show no signs of recovery.
In terms of practicality, there are better methods to interact with the end
customer and manage internal resources when a specific call to action is
required.
Without the power of business analytics, a lot of precious resources would
likely be wasted on customers who would eventually default on their
payments; however, with the power of business analytics, it becomes super
simple to have accurate predictions and to allocate internal resources to
ensure that all issues at hand are handled well.

4. Accounting Processes Are Simplified

To be honest, budgeting and investment decisions have a direct influence
on organizational success. As a result, you must back up these judgments
with statistical data and logic to guarantee that the firm does not incur
losses.
In this case, business analytics may assist you in managing tangible assets
while also shedding light on a company's financial performance. It
emphasizes sectors that consume a substantial portion of profits, such as
Page 53 of 150
 Page 54 of 150
power bills, tariffs, salaries, and so on.

Page 54 of 150
 Page 55 of 150

5. Enhances the Supply Chain

Supply chains, believe it or not, are a fantastic area to uncover possibilities
and commercial advantages. After all, they contribute significantly to the
company's cost structure.
As a result, by employing business analytics, you may discover possible
inefficiencies in traditional supply chain systems. Similarly, you may identify
abnormalities and check data to guarantee that deliveries are made on
schedule.
Furthermore, business analytics employs data and quantitative
approaches to improve decision making across the whole supply
chain.
To apply statistical approaches to all current data sources, you may
integrate enterprise resource planning. Aside from improving front-line
operations, data-driven processes may lead to better sales and inventory
planning.

BUSINESS ANALYTICS TOOLS

Database queries and analysis

-if” analyses

and text analytics

PROBLEM SOLVING WITH ANALYTICS

(To support Organizational Decision Making)
1. Recognize a problem
2. Define the problem
Page 55 of 150
 Page 56 of 150
3. Structure the problem

Page 56 of 150
 Page 57 of 150

4. Analyze the problem

5. Interpret results and make a decision
6. Implement the solution

1. RECOGNIZE A PROBLEM
Problems exist when there is a gap between what is happening and what we
think should be happening.

2. DEFINE THE PROBLEM

Clearly defining the problem is not a trivial task.

-large number of courses of action

-the problem belongs to a group and not an individual
-competing objectives
-external groups are affected
-problem owner and problem solver are
not the same person
-time limitations exist
What is part of the problem? What not?

3. STRUCTURE THE PROBLEM

Stating goalsand objectives

constraintsor restrictions
4. ANALYZE THE PROBLEM
Analytics plays a major role.

evaluating different scenarios, analyzing risks associated with various

decision alternatives, finding a solution that meets certain goals, or
determining an optimal solution.

Page 57 of 150
 Page 58 of 150

5. INTERPRET RESULTS AND MAKE DECISION

What do the results found by the model mean for the application?

the limitations of modelsand their underlying assumptions and often

incorporate judgment into making a decision.

6. IMPLEMENT THE SOLUTION

Translate the results of the model back to the real world.

to change, modifying organizational policies, and developing trust.

HOW TO DO AN ANALYTICS PROJECT

CRISP-DM REFERENCE MODEL
(refer below image)

Page 58 of 150
 Page 59 of 150

=================================================
===============

(1.5) BUSINESS ANALYTICS FOR COMPETITIVE ADVANTAGE.

Business Analytics processed in the following

five sources for competitive advantage.

1. Product Attribute Differentiation

Page 59 of 150
 Page 60 of 150

One way to gain an advantage over competitors is by differentiating your

product from theirs. Ask yourself: What makes my offering unique? Why
would consumers want to purchase my product instead of my competitors’?
Countless attributes can set your product apart. Here are some to consider:
 Better customer service
 More variety
 Faster or cheaper shipping
 Location
 Color and aesthetics
 Brand identity
 Atmosphere of brick-and-mortar locations
 Source of goods
Whole Foods Market is one example of a company that differentiates its
products using brand identity, atmosphere, and sourcing. Whole Foods’
competitors are other natural
food chains, such as Trader Joe’s and Sprouts Farmers Market, along with big
names in the grocery space, including Stop & Shop and Wegman’s.
Whole Foods stands out in the crowded natural foods market as the first and
only certified organic national grocery store in the United States. Its brand
identity centers on the integrity of its natural and organically sourced foods.
It also cultivates an in-store atmosphere that makes grocery shopping feel
purposeful and is a step up from some of its competitors' traditional grab-
and-go shopping experience.
Like Whole Foods, find the attributes that differentiate your product from
others and make them central to your brand’s identity.

2. Customers’ Willingness to Pay

The way you price your products or services can set you apart from your
competitors. When doing so, it’s vital to understand your customers’
willingness to pay.
Page 60 of 150
 Page 61 of 150
Willingness to pay (WTP) is the maximum price a customer is willing to pay
for a product or service. It can be a specific dollar amount or a price range.

Page 61 of 150
 Page 62 of 150

By determining your customers’ WTP, you can ensure you’re maximizing

profit without turning away customers.
In the context of competition, it’s important to view willingness to pay as a
strategic tool. If your customers are willing to pay the same amount for your
and your competitors’ products, consider what can be shifted to increase
their willingness to pay for yours.
For example, business support system company CSG reports (pdf) that 47
percent of consumers are willing to pay more for products that are
sustainably sourced. Among those consumers, five percent are willing to
pay double the price for a sustainable product over a non-sustainable one.
With the knowledge that certain factors could cause your customers’
willingness to pay to increase, you can strategically implement changes
that give your business a competitive edge.
Alternatively, if your competitor provides a product at the very top of
customers’ willingness to pay, you can gain a competitive advantage by
offering a lower price. Tread cautiously, because doing so could start a price
war in which you both continue to drop prices to win customers.

3. Price Discrimination
With an understanding of your customers’ willingness to pay, you may find
that different types of customers are willing to pay different amounts for
your products. In such cases, it can be useful to employ price discrimination,
which can be a valuable tool for expanding your company’s reach when
competing with others.
“Price discrimination is one of the most common and powerful price
strategies for companies,” says Harvard Business School Professor
Bharat Anand in the online course Economics for Managers.
In the course, Anand presents several examples of price discrimination,
including reduced prices for students, seniors, and veterans. These “special
case” prices present an opportunity for your company to earn customers
whose willingness to pay may be lower than that of its typical customers.
It’s worth noting that a lower price doesn’t always win consumers over—
Page 62 of 150
 Page 63 of 150
selecting a strategic price is crucial, but it’s just one factor they consider
when determining which product to buy.

Page 63 of 150
 Page 64 of 150

4. Bundled Pricing
Another pricing strategy that can prove to be advantageous is bundled pricing.
Bundled pricing is the practice of selling two or more products together in a
“bundle,” for which the cost is different than that of purchasing all of the
items separately.
Cable companies often leverage bundling. Purchasing voice, video, and
data services together often grants the customer a lower price than if they
were to purchase the services individually.
“How you think about the logic of pricing should depend on willingness to
pay,” Anand says in Economics for Managers. He presents the example of
bundling childcare and theater tickets.
“Put two products together that, when consumed jointly, increase
consumers’ willingness to pay,” he says. “You might be able to increase the
price for both just because it has so much more value for consumers.”
The way you price your products should be strategic, purposeful, and give
your business a leg up over its competitors.

5. Human Capital
A company is only as strong as its people. As such, hiring, training, and
retaining a team of skilled employees is a competitive advantage for any
business.
Putting in the time and care to select outstanding candidates for open
positions, train current employees, offer professional development
opportunities, and create a culture wherein people feel supported and
challenged can pay off.
Gallup reports that business units with highly engaged employees see a 21
percent increase in profit over their less-engaged counterparts.
Employee engagement has been especially important during the
coronavirus (COVID- 19) pandemic, as many businesses have closed
physical offices and transitioned to remote work. By finding ways to
effectively engage your team in a virtual setting, you can make them feel
Page 64 of 150
 Page 65 of 150
supported and empowered from afar.

6. POSITIONING YOUR BUSINESS FOR SUCCESS

Page 65 of 150
 Page 66 of 150

Differentiating your product, creating a pricing strategy, and investing in

your employees can be the difference between rising to the top of your
market and being driven out by a competitor.
By taking a strategy course, such as Economics for Managers, you can
bolster your skills in these areas and see competition not as a looming
threat, but as a catalyst for growth.
SOFTWARE SUPPORT IN BUSINESS ANALYTICS
SQLvarious databases

ExcelSpreadsheets

and other databases.

designed to meet the needs of midsize companies, provides reporting,

analysis, dashboard, scorecard, planning, budgeting and forecasting
capabilities.

Rapid Miner Predictive modeling and data mining, visualization,

forecasting, optimization and model management, statistical analysis, text
analytics, and more using visual workflows.

-based data preparation, analytics and visualization.

=================================================
===============
UNIT II
MANAGING RESOURCES FOR BUSINESS ANALYTICS

(Managing BA Personnel, Data and Technology. Organisational Structures

aligning BA. Managing Information policy, data quality and change in BA).

BUSINESS ANALYTICS USED IN HUMAN RESOURCE.

How is business analytics used in HR?
Page 66 of 150
 Page 67 of 150

HR analytics aim to provide insight into how best to manage employees and reach
business goals. Because so much data is available, it is important for HR teams to
first identify which data is most relevant, along with how to use it for maximum
ROI.

What is HR analytics?
HR analytics, also referred to as people analytics, workforce analytics, or
talent analytics, involves gathering together, analyzing, and reporting HR
data. It enables your organization to measure the impact of a range of HR
metrics on overall business performance and make decisions based on data.
In other words, HR analytics is a data- driven approach toward Human
Resources Management.
HR analytics is a fairly novel tool. This means it is still largely unexplored in
scientific literature. The best-known scientific HR analytics definition is by
Heuvel & Bondarouk. According to them, HR analytics is the systematic
identification and quantification of the people drivers of business outcomes (Heuvel &
Bondarouk, 2016). We discuss this further in our People Analytics Certificate
Program.
In the past century, Human Resource Management has changed
dramatically. It has shifted from an operational discipline towards a more
strategic one. The popularity of the term Strategic Human Resource
Management (SHRM) exemplifies this. The data- driven approach that
characterizes HR analytics is in line with this development.
By using people analytics you don’t have to rely on gut feeling anymore.
Analytics enables HR professionals to make data-driven decisions.
Furthermore, analytics helps to test the effectiveness of HR policies and
different interventions.
By the way, HR analytics is similar to people analytics but there are some
subtle differences in how the terms are used.
Being able to use data in decision-making has been growing in importance
throughout the global pandemic. Moving towards a post-pandemic world,
there are many changes happening in employment – whether it is the
Page 67 of 150
 Page 68 of 150
growing popularity of hybrid work or the increased use of automation. In this
age of disruption and uncertainty, it is vital to make the correct decisions in
order to navigate our new realities.

Page 68 of 150
 Page 69 of 150

Using data in HR
Of all the departments in an organization, the Human Resource (HR)
department may have the least popular reputation.
This has two reasons. First of all, the HR department is like a doctor: you’d
rather never need one.
Picture your role from the other side – when you ask an employee to come by
your
office, it’s likely that something bad is about to happen. You may need to
reprimand, put on notice, or even fire your colleague. Good news, like
getting a promotion, tends to come from an employee’s direct manager. Not
HR.
Secondly, many regard HR as soft. Fluffy-duddy. Old-fashioned. A lot of the
work in HR is based on ‘gut feeling’. We’re doing things a certain way
because we’ve always done it that way. HR doesn’t have a reputation of
bringing in the big bucks or playing a numbers game like sales. HR also
struggles to quantify and measure its success, as marketing and finance do.
HR data analytics changes all of this. A lot of the challenges we just
described can be resolved by becoming more data-driven and savvy about
HR and analytics.
Example questions include:
 How high is your annual employee turnover?
 How much of your employee turnover consists of regretted loss?
 Do you know which employees will be the most likely to leave your
company within a year?
These questions can only be answered using HR data. Most HR
professionals can easily answer the first question. However, answering the
second question is harder.
To answer this second question, you would need to combine two different
data sources: your Human Resources Information System (HRIS) and your
Performance Management System.
To answer the third question, you would need even more HR data and
extensively analyze it as well.

Page 69 of 150
 Page 70 of 150
As a HR professional, you collect vast amounts of data. Unfortunately, this
data often remains unused. Once you start to analyze human resource
challenges by using this data, you are engaged in HR data analytics.

Page 70 of 150
 Page 71 of 150

How HR analytics helps Human Resource Management

In the same way that analytics has revolutionized marketing, HR is being
transformed by analytics too. It enables HR to:
 Make better decisions using data
 Create a business case for HR interventions
 Test the effectiveness of these interventions
 Move from an operational partner to a tactical, or even strategic partner
The majority of HR departments just record, and store employee data. This
doesn’t suffice in today’s data-driven economy.
Simply keeping records is often insufficient to add any strategic value. In the
words of Carly Fiorina: “The goal is to turn data into information and
information into insight”. This also applies to HR.
Doing this enables HR to become more involved in decision-making on a
strategic level. The graphic below shows how this works in practice.

How to get started with HR analytics

Start with a straightforward question, such as “which employees have the
highest potential for progression and leadership?” You can answer this
question using quite
simple statistics. Doing this helps to quantify the relationships between
people’s abilities and organizational outcomes. In this way, analytics can
help your organization track absenteeism, turnover, burnout, performance
and much more.
Analytics makes HR (even more) exciting. The insights provided can lead
strategic decisions and optimize day-to-day business processes.
And if you know what makes your employees tick, you can create a better
work environment and identify future leaders. Imagine that you could
predict which employees are most likely to leave the company.
After asking the right question, you have to select the right data from your
different systems. This data is then combined, cleaned, and analyzed. This
analysis leads to insights.
Not all insights are equally interesting, or valuable. That’s why you need to
Page 71 of 150
 Page 72 of 150
ask questions about things your HR department can have an impact upon.
For example, you can’t change the wider economic trends, such as if your
country is currently in a

Page 72 of 150
 Page 73 of 150

recession. However, you do have influence over your management styles

and engagement levels. Asking the right questions leads to actionable
insights.

How does HR analytics shape the business?

You can imagine that HR data analytics holds enormous value for an
organization. These examples are only the beginning. Indeed, analytics
enables companies to measure the business impact of people policies.
By applying complex statistical analyses, HR can predict the future of the
workforce. This enables managers to measure the financial impact of
Human Resource practices. To read more about the tools used for these
analyses, check our overview on the top HR analytics tools.
Measuring the impact of HR on bottom-line performance is the “holy grail”
of HR data analytics (Lawler III, Levenson & Boudreau, 2004). This is often
done by calculating a Return on Investment (ROI). It is the most powerful
way for HR to increase its strategic influence.
The aforementioned examples have an impact on both the cost and the
revenue side of the business.

Knowing the impact of HR policies will also help HR to become a strategic

partner and get rid of its ‘soft’ image. It helps HR to align its strategy with
business goals and to quantify the value it adds to the business. It takes
the guess-work out of HR.
So, how do we at Analytics in HR define HR analytics? We believe it is about
identifying the people-related drivers of business performance. It takes the
guesswork out of employee management and is, therefore, the future of HR.
Or, to put it in the words of Edwards Deming: “Without data you’re just
another person with an opinion”.
=================================================
==============

(2.2)ORGANISATIONAL STRUCTURES ALIGNING BUSINESS ANALYTICS

Page 73 of 150
 Page 74 of 150

Organizational Analytics is the process or set of processes that links people and
organization to the creation of value through information – information generated

Page 74 of 150
 Page 75 of 150

through applying statistics, computer programming, organizational

behaviour & human resource principles and decision science methods.

Organisational Structures aligning Business Analytics

 Product management: Responsible for designing the analytics
products and solutions including product/solution backlogs
prioritization and management, coming up with success criteria and
success metrics, tracking and reporting the success metrics
 Data architecture: Overall design of the data environment to serve the
needs of the enterprise
 Data management & governance: Building, maintaining, and governing
the data environment. Data management is tightly tied into business
analytics data architecture
 Reporting: Standardized, periodic renderings of data relationships
and related metrics; Reporting is needed to convey business
information effectively and quickly to users at regular intervals.
 Ad-hoc analysis: Directed analysis to answer a specific question. Ad-
hoc data analysis is required to meet specific business user demands
in real-time
 Advanced analytics: Advanced analysis of data leveraging
predictive (AI, machine learning, data science) and
prescriptive analytics.
Data mining is integral to successful reporting, ad-hoc analysis, and
advanced analytics. Data mining refers to the process of extracting useful
information from data or mining insights.
=================================================
==============

(2.3) MANAGING INFORMATION POLICY, DATA QUALITY AND CHANGE IN

BUSINESS ANALYTICS

Page 75 of 150
 Page 76 of 150
MANAGING INFORMATION POLICY
What is an information management policy?

Page 76 of 150
 Page 77 of 150

An information management policy gives staff direction for creating, capturing

and managing information assets (records, information and data) to satisfy
business, legal and stakeholder requirements. It also assigns responsibilities
across the agency.

How do policies and procedures relate to the management of information?

Policies cover data protection, records management and information security.
You make operational procedures, guidance and manuals readily available
to support data protection policies and provide direction to operational
staff. Policies and procedures clearly outline roles and responsibilities.

What is an information management policy?

An information management policy gives staff direction for creating, capturing
and managing information assets (records, information and data) to satisfy
business, legal and stakeholder requirements. It also assigns responsibilities
across the agency.

What is an information management procedure?

An Information Management Process is the method an organisation uses
to: Acquire or retrieve information. Organise information. Maintain information.

What is an information management policy?

An information management policy gives staff direction for creating,
capturing and managing information assets (records, information and data)
to satisfy business, legal and stakeholder requirements. It also assigns
responsibilities across the agency.
An information management policy should be consistent with the principles,
environment and strategic directions described in your agency's information
governance framework.
The Building trust in the public record policy recommends that agencies update
their information governance framework to include enterprise-wide
information management (action 2).
Page 77 of 150
 Page 78 of 150

Developing or updating your agency’s information management policy should be

part of implementing this governance framework.
An information management policy:
 sets out your agency’s expectations for fit for purposes information
management practices, processes and systems that will support the
management of information as an organisational asset
 explains the benefits of good information management
 outlines roles and responsibilities
 proves commitment to meeting business, legislative and regulatory
requirements
 contributes to an environment that values the integrity and
accessibility of information assets to support the delivery of
business outcomes.
When developing your information management policy, consider how it
supports your agency’s strategic objectives and intersects with other
strategic documents.
How your information management policy integrates with other policy and
governance documents can be influenced by the size and nature of your
agency. It should be designed to best meet the size, nature and complexity
of your agency’s business. For example, a smaller agency may combine the
information management policy with other governance documents. A larger
agency, or one with a more complex information management environment,
may have separate governance documents complemented by other policies
on aspects of information management. This can be useful when different
policy statements are directed at different audiences, to ensure they are
aware of their specific require

Things to include
An effective information management policy will usually include the following:
 details of organisationally endorsed processes, practices and
procedures for undertaking information management tasks,
including creation and capture

Page 78 of 150
 Page 79 of 150
 identification of endorsed systems for managing information assets
 advice on the disposal and destruction of information assets,
including the provisions of normal administrative practice (NAP)

Page 79 of 150
 Page 80 of 150

 an outline of the roles, responsibilities and expectations of all staff in

managing information assets, in addition to detailed guidance for
specific position holders as needed.

Interaction with other policies and procedures

Given the complexity of information management, it is likely that it will take
more than one policy document to provide guidance across all processes.
Information management policy statements should be embedded into a
broad range of organisational policies and procedures, to assist ease of
access by stakeholders.
Dividing policy statements across several documents can also enhance
readability by focusing on one area of information management.
For example:
 A Data Migration Policy could lay out considerations for information
technology teams migrating data from one business system to
another. This may include guidance around interoperability, quality
assurance testing, metadata controls and accountable destruction of
data, if all data is not being migrated.
 A Normal Administrative Practice Policy would provide advice to staff
on which information assets they can routinely destroy. It would
outline the types of low- value and short-term information that can
be destroyed in the normal course of business.
 An Information Technology Procurement Policy may include a policy
statement that requires newly procured business systems to be
compliant with
the Australian Government Minimum Metadata Set.

Key aspects of an information management policy

Title, date and version number
Follow your agency’s naming and versioning conventions and identify how
frequently the policy will be reviewed.
Purpose
Page 80 of 150
 Page 81 of 150
Explain why an information management policy is needed and the benefits
of good practice.
For example:

Page 81 of 150
 Page 82 of 150

The purpose of this policy is to guide and direct the creation and
management of information assets (records, information and data) by staff,
and to clarify staff responsibilities. [The agency] is committed to
establishing and maintaining information management practices that meet
its business needs, accountability requirements and stakeholder
expectations.
The benefit of complying with this policy will be trusted information that is
well- described, stored in known endorsed locations and accessible to staff
and clients when needed.
This policy is written within the context of [the agency's] information
governance framework, which is located at XXXX. Complementary policies
and additional guidelines and procedures support this policy and are located
at XXXX.

Scope
The scope should identify both who and what is covered by the policy, to
support the holistic management of all an agency’s information assets.
For example:
This policy applies to all [agency] staff members and contractors and to all
information assets (records, information and data) in any format, created or
received, to support [agency] business activities.
It covers all business applications used to create, manage and store
information assets, including dedicated information management systems,
business information systems, databases, email, voice and instant
messaging, websites, and social media applications. This policy covers
information created and managed in-house and off-site, including in cloud
based platforms.

Policy statement
Provide a brief statement of your agency's commitment to good
information management practices. If it applies, briefly mention factors
Page 82 of 150
 Page 83 of 150
that influence information management within the agency.
For example:

Page 83 of 150
 Page 84 of 150

[The agency] recognises its information assets as valuable corporate assets

and is committed to achieving appropriate and ongoing management of
these assets to advance [the agency’s] strategic priorities and meet client
needs.
or
There is an expectation that [the agency] will [mention here any obligations
that apply specifically to your agency]. It is committed to creating and
keeping accurate and reliable information to meet this obligation.
Also, [the agency] is committed to the principles and practices set out in
whole-of- government policies and best-practice standards. Our agency will
implement fit-for- purpose information management practices and systems
to ensure the creation, maintenance and protection of reliable information.
All information management practices in [this agency] are to align this
policy and its supporting procedures.

Legislation and other key mandates

Your information governance framework should cover your agency’s legal,
regulatory and business environment. Your information management policy
should only cite directions and requirements that directly affect staff or are
necessary for them to understand the policy’s operating environment. An
example could be agency-specific legislative requirements for creating or
keeping particular information. In general, the policy should refer staff to
the relevant sections of the framework and strategy rather than repeating
them.
For example:
All staff must take steps to protect personal information according to the
Privacy Act 1988 and the Australian Privacy Principles. This includes
personal information stored in cloud-hosted services.

Creation and management of information assets

Provide guidance on the type of information assets that need to be created,
captured and managed to support agency business and compliance with
Page 84 of 150
 Page 85 of 150
legal requirements. Operational work groups may have specific
requirements to create and capture information which are documented in
business procedures. These should be referenced, but not reproduced, in
the policy.

Page 85 of 150
 Page 86 of 150

Other guidance that could be covered in the policy includes:

 Endorsed systems used to maintain information: establish clearly
which locations are endorsed for the capture and storage of
information and which should not be used. For example, corporate
information assets must not be maintained in email folders, shared
folders, personal drives or external storage media.
 Requirements for storage and preservation: for information in digital
and physical formats, including security protocols and preservation
requirements. This may include referencing preferred file formats.
 Access to information: provide a statement supporting staff having
ready access to corporate information. Describe situations when it is
appropriate to restrict this access. Document the public’s right of
access to information under legislation including the Freedom of
Information Act 1982 and the Archives Act 1983. Describe how your
agency supports public release of information assets, for example,
under the Information Publication Scheme or to meet Australian
Government commitments to release publicly available datasets.
 Retention and destruction: describe the responsibilities staff have for
retaining and destroying the organisation's information assets.
Provide staff with the information they need to comply with
accountable and authorised destruction of information assets. This
includes the correct use of normal administrative practice (NAP).
 Transfer: outline instances when information may be required to be
transferred. Explain that information assets of archival value are
transferred to the care of the National Archives, but access can be
arranged for staff if they are needed. Note that information may be
transferred to other agencies as a result of a machinery of
government change.
In all cases, any supporting guidelines, procedures or related documents
should be linked to the policy document.
Roles and responsibilities
Define the roles and responsibilities of all agency employees to ensure that
Page 86 of 150
 Page 87 of 150
reliable and usable information is created and managed, and is kept for as
long as it is needed for business, accountability or historical purposes. This
may include statements such as:

Page 87 of 150
 Page 88 of 150

All staff: responsible for the creation and management of information as

defined by this policy.
Additional responsibilities for certain staff are listed below:
Agency head: responsible for information governance within the agency. The
agency head has authorised this policy. The agency head promotes
compliance with this policy, delegates responsibility for the operational
planning and running of information management to a senior executive
officer in the organisation, and ensures the agency's information
management program of activities is adequately resourced.
Chief Information Governance Officer (CIGO): responsible for the
establishment and maintenance of an enterprise-wide culture for an
accountable and business-focused information management environment
Senior management: responsible for visible support of, and adherence to, this
policy by promoting a culture of accountable information management
within the organisation. This includes senior executive officers and
managers.
Information management unit: under the leadership of the delegated senior
executive, the information management unit is responsible for overseeing
the management of information assets (records, information and data) in
this organisation consistent with the requirements described in the policy.
This includes:
 providing training, advice and general support to staff
 creating, developing or acquiring and implementing information
management products and tools, including systems to help create
complete and accurate information
 developing and implementing strategies to enable sound
information management practices
 monitoring compliance with information management policies and directives
 advising senior management of any risks associated with non-
compliance. ICT staff: responsible for maintaining the technology for [the
agency's] business information systems, including maintaining
appropriate system accessibility, security and backup. ICT staff should
Page 88 of 150
 Page 89 of 150
ensure that any actions, such as removing information
assets from systems or folders, are undertaken in accordance with this
policy. ICT and information management staff have an important joint role
in ensuring that systems support accountable and effective information
management across the organisation.

Page 89 of 150
 Page 90 of 150

Agency security advisor: provides advice on security policy and guidelines

associated with the management of information.
Managers and supervisors: responsible for ensuring staff, including contract
staff, are aware of, and are supported to follow, the information
management practices defined in this policy. They should advise the
information management unit of any barriers to staff complying with this
policy. They should also advise the unit of any changes in the business
environment that would impact on information management requirements,
such as new areas of business that need to be covered by a records
authority.
Contract staff: create and manage information assets in accordance with this
policy to the extent specified in their contract.
Communication and training
Include a statement affirming that the policy will be communicated to staff
and that training will be provided on aspects of the policy. When
conducting training, keep it up- to-date, schedule it regularly and consider
how to tailor it so that it is meaningful to different work groups in your
agency.
Mention any separate information or training available on aspects of
information management, such as titling, capture, or how to incorporate
the policy’s directions into business procedures and workflows.
Monitoring and review
Make a commitment to review the policy and monitor compliance. When
reviewing the policy, consider its relevance, if it is still appropriate and staff
awareness of its requirements. Monitor staff adoption of the policy at
regular intervals. If direct supervisors are responsible for monitoring staff
compliance, ensure they are aware of their responsibility and the standards
expected of their staff.
For example:
This policy will be updated as needed if there are any changes in the
business or regulatory environment. It is scheduled for a comprehensive
review by 20XX. The head of the information management unit will initiate
Page 90 of 150
 Page 91 of 150
this review and the information governance committee will conduct it.
The information management unit [with the support of workplace
supervisors] will monitor compliance with this policy. Levels of
compliance will be reported at least annually to senior management.

Page 91 of 150
 Page 92 of 150

Resources
Provide a list of resources that give extra information. This may include
contact details of relevant staff within the agency, as well as useful
reference material.
Senior management endorsement
Provide evidence that the head of your agency or a senior officer with
responsibility for information management has endorsed the policy. This
may be done in a brief paragraph signed by the head of agency or senior
officer, recognising the important place of information management in the
agency and directing staff to comply with the requirements of the policy.
=================================================
=============
(2.4) WHAT IS DATA QUALITY AND MASTER DATA MANAGEMENT?

EXAMPLES OF DATA SOURCES AND USES

Internal

audits

External

New developments: Web behavior –Social Media –Mobile -IOT

, length of time, origin and destination
paths, products they searched for and viewed, products purchased, what
reviews they read, and many others.

WHAT IS BIG DATA

Big data to refer to massive amounts of business data from a wide variety of
sources, much of which is available in real time, and much of which is
Page 92 of 150
 Page 93 of 150
uncertain or unpredictable. IBM calls these characteristics volume, variety,
velocity,and veracity.

Page 93 of 150
 Page 94 of 150

“The effective use of big data has the potential to transform economies, delivering a
new wave of productivity growth and consumer surplus. Using big data will become a
key basis of competition for existing companies, and will create new competitors who
are able to attract employees that have the critical skills for a big data world.” -
McKinsey Global Institute, 2011

DATA SETS AND DATABASES

Database-a collection of related tables containing records on people, places, or
things.
◦ In a database table the columns correspond to each individual element of data
(called
fields,orattributes), and the rows represent records of related data elements.
EXTRACT FROM SQL
Data set-a collection of data (often a single “spread sheet” or data mining table).
◦ Examples: Marketing survey responses, a table of historical stock
prices, and a collection of measurements of dimensions of a
manufactured item.

TYPES OF DATA
Discrete-derived from countingsomething.
◦ For example, a delivery is either on time or not; an order is complete or
incomplete; or an invoice can have one, two, three, or any number of
errors. Some discrete metrics would be the proportion of on-time deliveries;
the number of incomplete orders each day, and the number of errors per
invoice.
Continuous based on a continuous scale of measurement.
◦ Any metrics involving dollars, length, time, volume, or weight, for
example, are continuous.

MEASUREMENT SCALES
Categorical (nominal) data -sorted into categories according to

Page 94 of 150
 Page 95 of 150
specified characteristics.

Ordinal data -can be ordered or ranked according to some relationship to

one another.

Page 95 of 150
 Page 96 of 150

Interval data -ordinal but have constant differences between observations

and have arbitrary zero points.

Operations have meaning

Ratio data -continuous and have a natural zero.
Equality: Are values the same?
Sort: Is one value larger/better?
Median Addition/Subtraction:
E.g. Average
Multiplication:E.g. % change

DATA RELIABILITY AND VALIDITY

Reliability-data are accurate and consistent.
Validity-data measures what it is supposed to measure.
Examples:
◦ A tire pressure gage that consistently reads several pounds of pressure
below the true value is not reliable, although it is valid because it does
measure tire pressure.

◦ The number of calls to a customer service desk might be counted

correctly each day (and thus is a reliable measure) but not valid if it is
used to assess customer dissatisfaction, as many calls may be simple
queries.
◦ A survey question that asks a customer to rate the quality of the food in a
restaurant may be neither reliable (because different customers may have
conflicting perceptions) nor valid (if the intent is to measure customer
satisfaction, as satisfaction generally includes other elements of service
besides food).

DATA QUALITY
can be defined in many different ways. In the most general sense, good
data quality exists when data is suitable for the use case at hand.
Page 96 of 150
 Page 97 of 150
This means that quality always depends on the context in which it is used, leading
to the conclusion that there is no absolute valid quality benchmark.
Nonetheless, several definitions use the following rules for evaluating data quality:

Page 97 of 150
 Page 98 of 150

 Completeness: are values missing?

 Validity: does the data match the rules?
 Uniqueness: is there duplicated data?
 Consistency: is the data consistent across various data stores?
 Timeliness: does the data represent reality from the required point in time?
 Accuracy: the degree to which the data represents reality
In the context of business intelligence / business analytics, the goal of
master data management is to bring together and exchange master data
such as customer, supplier or product master data from disparate
applications or data silos. Master data management is needed …
 … because aside from a “master” ERP system, many companies
work with other CRM or SCM systems or Web services. Master data
management assures data consistency across these systems;
 … to easily integrate systems following corporate mergers and acquisitions;
 … to cooperate effectively with business partners;
 … to provide an optimal customer experience;
 … to build a 360 degree customer view that addresses customer
needs in the best way possible;
 … to merge on-premise and cloud-based systems.

WHY DATA QUALITY AND MASTER DATA MANAGEMENT ARE IMPORTANT

Valid data lies at the heart of the strategic, tactical and operational steering
of every organization. Having appropriate data quality processes in place
directly correlates with an organization’s ability to make the right decisions
and assure its economic success. As The BI Survey data shows, companies
have always struggled to ensure a high level of data quality. But in today’s
digital age, in which data is increasingly emerging as a factor of production,
there is growing pressure to use or produce high quality data.
Here are just a few of the growing challenges for data quality in today’s
companies:

Page 98 of 150
 Page 99 of 150
 Employees do not work with their BI applications because they do not
trust them (and/or their underlying data)

Page 99 of 150
 Page 100 of
150
 Incorrect data leads to false facts and bad decisions in
data-driven environments
 If data quality guidelines are not defined, multiple data copies are
generated that can be expensive to clean up
 A lack of uniform concepts for data quality leads to
inconsistencies and threatens content standards
 For data silo reduction, uniform data is necessary to allow systems
to talk to each other
 To make Big Data useful, data needs business context; the link to the
business context is master data (e.g., in Internet of Things use cases,
reliable product master data is absolutely necessary)
 Shifting the view to data (away from applications) requires a
different view on data, independent from the usage context so there
are general and specific requirements for the quality of data
Furthermore, there are specific characteristics in today’s business world that push
the organization to think about how to collect reliable data:
 Companies must be able to react as flexibly as possible to dynamically
changing market requirements. Otherwise, they risk missing out on
valuable business opportunities. Therefore, a flexible data landscape
that can react quickly to changes and new requirements is essential.
Effective master data management can be the crucial factor when it
comes to minimizing integration costs.
 Business users are demanding more and more cross-departmental
analysis from integrated datasets. Data-driven enterprises in
particular depend on quality-ensured master data as a pre-requisite
to optimize their business process and develop new (data-driven)
services and products.
 Rapidly growing data volumes, as well as internal and external data
sources, lead to a constantly increasing data basis. Transparent
definitions of data and its relationships are essential for managing
and using them.
 Stricter compliance requirements make it more important than ever
Page 100 of
150
 Page 101 of
to ensure that data quality standards are met. 150

Page 101 of
150
 Page 102 of
150
To make matters worse, the analytical landscapes of organizations are
becoming more complex. Companies collect increasing volumes of
differently structured data from various sources while at the same time
implementing new analytical solutions.
This drastically increases the importance of consistent master data.
Companies can only unlock the full economic potential of their data if the
master data is well managed and provided in high quality.

HOW TO ACHIEVE A HIGH LEVEL OF (MASTER) DATA QUALITY

Successful data quality and master data management initiatives require a

holistic approach.
Organizations need to address persons, processes and technology to
implement the business demands on data quality:
 The organization should include clear responsibilities for data
domains (e.g., customer, product, financial figures), as well as roles
(data owner, operational data quality assurance / data stewards).
 Processes for data quality assurance can be defined by adopting best
practices like the data quality cycle.
 Technology supports people in their processes via software features
and the requisite IT architecture.
It is important to consider business obligations first and keep in mind that
the organization and its processes are always more important than the
technology since they are defined according to company strategy. So
technology is simply there to support them.

ORGANIZATION OF DATA QUALITY AND MASTER DATA MANAGEMENT

When it comes to improving data quality, a company culture that
recognizes data as a key production factor for generating insights is
essential.
In the context of data quality and master data management, the
responsibility for data plays a crucial role.
Page 102 of
150
 Page 103 of
150
Role concepts help with the definition and assignment of tasks and
competencies to certain employees. By assigning certain roles, the
company can ensure that responsibility for accurate data and its care is
clear and enduring.
Typical roles for ensuring data quality and master data management are:
 The data owner is the central contact person for certain data
domains. He defines requirements, ensures data quality and
accessibility, assigns access rights and authorizes data stewards
to manage data.
 The data steward defines rules, plans requirements and coordinates
data delivery. He is also responsible for operational data quality, for
example checking for duplicate values.
 The data manager is usually a member of the IT department. He
implements the requirements of the data owner, manages the
technological infrastructure and secures access protection.
 All being well, data users from business departments or IT have
access to reliable and understandable data.
Each role involves clear tasks that are geared towards company-specific goals.

PROCESSES FOR DATA QUALITY AND MASTER DATA MANAGEMENT

The best practice process for improving and ensuring high data quality
follows the so- called data quality cycle.
The cycle is made up of an iterative process of analyzing, cleansing and
monitoring data quality. The concept of a cycle emphasizes that data
quality is not a one-time project but an ongoing undertaking.
The data quality cycle is made up of the following phases:
 At first data quality goals or metrics needs to be defined according to
business needs. These goals should form part of the overall data
quality strategy as well. There should be a clear understanding of what
data should be analyzed. Does a lack of completeness for some data
really matter? What attributes are required for data to be complete?
How can a data domain (e.g., a customer) be defined?
Page 103 of
150
 Page 104 of
 150 data
Then the data is analyzed: questions like “which values can the
have?” or “is the data valid and accurate?” need to be addressed.

Page 104 of
150
 Page 105 of
150
 The cleansing of the (master) data is normally done according to
engineered individual business rules.
 Enrichment of data (with, for example, geo-data or socio-
demographic information) can help with systems and
business processes.
 To ensure (master) data quality is reached, continuous monitoring and
checking of the data is very important. This can be done automatically
via software by applying defined business rules. So at the end of the
cycle, there is a fluent transition of the original data quality initiative
to the second phase:
the ongoing protection of data quality.
The different phases are typically assigned to the aforementioned roles.
DATA QUALITY AND MASTER DATA MANAGEMENT SOFTWARE
Most of the technologies on the market today are aligned with the data quality
cycle and provide in-depth functionality to assist various user roles in their
processes.
The best way of achieving high data quality with technology is to integrate
the different phases of the data quality cycle into operational processes
and match them with individual roles. Software tools assist in different
ways by providing:
 Data profiling functions
 Data quality functions like cleansing, standardization, parsing, de-
duplication, matching, hierarchy management, identity resolution
 User-specific interfaces/workflow support
 Integration and synchronization with application models
 Data cleansing, enrichment and removal
 Data distribution and synchronization with data stores
 Definition of metrics, monitoring components
 Data Lifecycle Management
 Reporting components, dashboarding
 Versioning functionality for datasets, issue tracking, collaboration
This list of functions is intended to give an overview of the functional range
Page 105 of
150
 Page 106 of
150
offered by current data quality and master data management tools.
Based on your company’s individual requirements, every organization should
define and prioritize which specific functions are relevant to them and which
will have a significant impact on the business.

Page 106 of
150
 Page 107 of
150
The market for data quality and master data management tools is
comparatively heterogeneous. Providers can be classified according to
their focus or their history in the following groups:
 Business intelligence and data management generalists have a
broad software portfolio which also can be used for data quality
and master data management tasks.
 Specialists of service-oriented infrastructures also offer software
platforms, which can be used to manage master data.
 Data quality specialists are mainly focused on how data quality can be
ensured and provide tools that can be integrated into existing
infrastructures and systems.
 Data integration specialists offer tools that are especially useful for
matching and integrating data from different systems.
 For master data management specialists, master data
management is a strategic topic. These providers offer explicit
solutions and services for the management of master data.
 Data Preparation (Data Pre-Processing for Data Discovery) is a relatively
new trend in the business intelligence and data management market.
In the context of data quality, data discovery software can be a flexible
(but not really durable) tool for business users to address data quality
problems.

DATA QUALITY AND MASTER DATA MANAGEMENT INITIATIVES IS THE SUCESS

OF SEVERAL COMPANIES.
Many companies are still afraid of data optimization projects such as data
quality and master data management initiatives. The organizational,
procedural and technological adjustments that have to be made can seem
too complex and incalculable.
On the other hand, companies that have successfully run data quality and
master data management initiatives achieved their success because they
simply took the decision to launch their initiative and then evolved step by
step.
Page 107 of
150
 Page 108 of
Companies suffering data quality problems should start by defining150
a short
set of guidelines in which they acknowledge that the age of digitization
requires rethinking and that data must be viewed as an important
production factor.

Page 108 of
150
 Page 109 of
150
According to the business or company strategy, corresponding initiatives
should be launched (e.g., create centrally available master data;
documented data domains, dimensions and KPIs; define contact persons
and data management processes).
With the success of these initiatives (higher data quality), the company will
notice improvements in its internal business processes (e.g., management
and sales departments will make decisions based on correct data instead of
“gut feeling”), as well as new potentials like the chance to make the
transition to becoming a digitalized company that is able to develop new
data-centric products and services for business partners.
Only data-driven companies can compete in the era of digitization. In the
increasingly complex world of data, enterprises need reliable pillars. Reliable
data is a critical factor. Ultimately, sustainable data quality management will
pay off.
===========================================
==================== (2.5) CHANGES MAY BE
REQUIRED IN BUSINESS ANALYTICS -
THE ROLE OF BUSINESS ANALYTICS IN CHANGE MANAGEMENT

We live in a global, interconnected economy. Shifting market conditions,

customer demands, and evolving technologies mean that businesses
constantly have to change to keep up. Now, thanks to the seachange
forced upon businesses by the COVID-19 pandemic, organizations are
having to adapt quickly to survive.
However, change is scary, and if it’s managed with poor communication, it
will inevitably lead to chaos. Having a business analyst (BA) acting as a
strategic component of your change management process can be critical to
successful change implementation.
As valuable as BAs are to change management, they’re often misunderstood.
Learn the role BAs play in change management and see how they can
deliver data and insights during this critical decision-making time.

Page 109 of
150
 Page 110 of
150
WHAT IS A BUSINESS ANALYTICS / BUSINESS ANALYST?
Business analysts provide business improvement recommendations based
on data. They use data analytics to examine processes, determine desired
outcomes, and deliver data-driven suggestions and reports to executives
and stakeholders. Business analysts evaluate the current model of a
business and see how it can be optimized.

Page 110 of
150
 Page 111 of
150
The real value of a business analyst is in mitigating risk and providing
strategic direction. That first part really can’t be overstated: risk mitigation
is key to the process of change management. Change introduces the
unknown to an environment and that can either spell success or disaster. A
good business analyst will minimize uncertainty and guide the organization
toward a greater likelihood of success.
What is change management?
Change management is, put simply, the process of guiding the adaptation
of a business. A business that has grown stagnant and too comfortable with
the way it operates will not survive the years to come. The evidence of that
is all around us, from department stores not willing to re-evaluating how
modern customers shop to restaurants that don’t offer delivery.
Change management is the process of re-evaluating your current business
model and implementing the pivots necessary to keep the business healthy
and competitive in an evolving market. Done well, change management
minimizes the fear of change that inevitably arises and gets everyone on
board with successful implementation.

Change management consists of five components:

1. Vision–The desired future state of the business.
2. Skills–The skills currently available within the organization.
3. Incentives–The reasons for change.
4. Resources–People and processes available to help guide the change.
5. Plan–A comprehensive set of steps for implementing the change
Once these five components have been deployed, the business can
measure the impact of the change and conduct valuable post-mortems.

BA change management tasks

What exactly does a business analyst do? Provide the expertise needed to make
smart, impactful change. Here’s how:
Identifying and clarifying the current state of the business
Page 111 of
150
 Page 112 of
150
Too often, organizations base their understanding of themselves on a
myopic, inside- out view. A business analyst provides an objective, data-
backed look at the actual state

Page 112 of
150
 Page 113 of
150
of your company: in other words, how healthy it is from a financial
perspective. A BA can tell you how much money your business has on hand,
what its debts are, and what your cash flow looks like. This is valuable for
being able to make a rational decision based on facts and not conjecture.
Providing current data on the state of the market
A BA will also provide an objective look at where your business stands in
context. It’s easy to feel, for instance, that your business is the top
cheesemaker in the country if you never research other cheesemakers. So,
a business analyst may look at market movement and use data to predict
future trends.
For instance, a business analyst may tell you that your business should
target enterprise companies instead of SMBs because your software is
more appropriate for large-scale solutions and enterprise companies tend
to have greater cashflow than SMBs. With that information, it’s easier to
not only decide which route is best for your company in the present
moment, but which changes will have favorable outcomes for years to
come.
Researching how proposed changes might impact the business
Business analysts aren’t fans of conjecture. Instead, they’ll use data to
simulate likely outcomes based on various fact-based scenarios. For
instance, a business analyst may simulate what kind of impact raising your
product pricing by 10% would have on everything from your bottom line to
your competitive place in the market. A BA will give you an educated opinion
based on all available data so that you can make informed decisions.
Collecting use cases
A BA can also help your business develop use cases. A use case is
essentially how an actor (normally a customer) interacts with a system to
achieve a desired end. If your business wants to understand, for instance,
how customers are interacting with a purchasing process, a business analyst
can look at the use case as well as alternate flows and exception flows to
uncover gaps in the process or missed opportunities. This is useful for
helping others think from the user’s perspective and describe the end result
Page 113 of
150
 Page 114 of
150 way
after the use case has been completed. In short, they give you a visual
to understand flows so your business can maximize them.
Defining and communicating the desired future state

Page 114 of
150
 Page 115 of
150
Sometimes organizations don’t know what they want. They certainly want to make
more money, but that’s not the entire story. It’s up to a BA to help define what an
organization actually wants.
For instance, consider a company that currently makes dashboards for self-
driving cars. Sure, the company wants a healthier bottom line. But what they
might really want is partnerships with prominent car manufacturers,
complete market domination, and to lead a transportation revolution. A BA
can help define and articulate the big, audacious desires of an organization.
That vision of a desired future state will inform the best changes the
business can make to achieve that future state.
Creating a comprehensive plan
It’s not enough for a business to know what needs to change. They also need
to know how to change. A business analyst can look at all the moving parts
in an organization and define their role in the change, how they contribute to
the implementation, and what the expectations are around contributing to
the change. They can create a clear, actionable plan that makes sense to
everyone involved.
Preparing reports and presentations to communicate motivations, changes,
options, and impact
An especially valuable role of BAs in change management is that of
showing why a business should change. They present their data and
rationale in reports and presentations to gain buy-in from stakeholders.
Seeing change options in a visual manner is vital when communicating both
the motivation for the change and its potential impact. It’s also a great idea
to create a
visual flowchart of the comprehensive plan mentioned above so that
there’s no doubt about how the implementation will proceed. These
presentations help eliminate confusion and uncertainty.
As you can see, a business analyst is truly vital to assisting your business in
navigating the world of change management. They can aid in everything
from providing data-driven suggestions for meaningful change to providing
roadmaps for how best to implement
Page 115 of
150
 Page 116 of
the change. They’re an invaluable investment in your business and150
can provide
the right strategy to keep the organization healthy throughout any crisis or time of
change.

Page 116 of
150
 Page 117 of
150
=================================================
=================
=================================================
=============
UNIT III
DESCRIPTIVE ANALYTICS
(Introduction to Descriptive analytics - Visualising and Exploring Data -
Descriptive Statistics - Sampling and Estimation - Probability Distribution for
Descriptive Analytics - Analysis of Descriptive analytics)

What is descriptive analysis analytics?

Descriptive analytics is the process of using current and historical data to
identify trends and relationships. It's sometimes called the simplest form of
data analysis because it describes trends and relationships but doesn't dig
deeper.

WHAT IS DESCRIPTIVE ANALYTICS? 5 EXAMPLES

Data analytics is a valuable tool for businesses aiming to increase revenue,
improve products, and retain customers. According to research by global
management consulting firm McKinsey & Company, companies that use
data analytics are 23 times more likely to outperform competitors in terms
of new customer acquisition than non- data-driven companies. They were
also nine times more likely to surpass them in measures of customer
loyalty and 19 times more likely to achieve above-average profitability.
Data analytics can be broken into four key types:
 Descriptive, which answers the question, “What happened?”
 Diagnostic, which answers the question, “Why did this happen?”
 Predictive, which answers the question, “What might happen in the future?”
 Prescriptive, which answers the question, “What should we do next?”
Each type of data analysis can help you reach specific goals and be used in
tandem to create a full picture of data that informs your organization’s
strategy formulation and decision-making.

Page 117 of
150
 Page 118 of
150
Descriptive analytics can be leveraged on its own or act as a foundation for
the other three analytics types. If you’re new to the field of business
analytics, descriptive analytics is an accessible and rewarding place to
start.

Page 118 of
150
 Page 119 of
150

WHAT IS DESCRIPTIVE ANALYTICS?

Descriptive analytics is the process of using current and historical data to
identify trends and relationships. It’s sometimes called the simplest form
of data analysis because it describes trends and relationships but doesn’t
dig deeper.
Descriptive analytics is relatively accessible and likely something your
organization uses daily. Basic statistical software, such as Microsoft Excel or
data visualization tools, such as Google Charts and Tableau, can help parse
data, identify trends and relationships between variables, and visually
display information.
Descriptive analytics is especially useful for communicating change over
time and uses trends as a springboard for further analysis to drive decision-
making.
Here are five examples of descriptive analytics in action to apply at your
organization.

5 EXAMPLES OF DESCRIPTIVE ANALYTICS

1. Web Traffic and Engagement Reports
One example of descriptive analytics is reporting. If your organization
tracks engagement in the form of social media analytics or web traffic,
you’re already using descriptive analytics.
These reports are created by taking raw data—generated when users
interact with your website, advertisements, or social media content—and
using it to compare current metrics to historical metrics and visualize
trends.
For example, you may be responsible for reporting on which media channels
drive the most traffic to the product page of your company’s website. Using
descriptive analytics, you can analyze the page’s traffic data to determine
the number of users from each source. You may decide to take it one step
further and compare traffic source data to historical data from the same
sources. This can enable you to update your team on movement; for

Page 119 of
150
 Page 120 of
150 20
instance, highlighting that traffic from paid advertisements increased
percent year over year.
The three other analytics types can then be used to determine why traffic
from each source increased or decreased over time, if trends are predicted
to continue, and what your team’s best course of action is moving forward.
2. Financial Statement Analysis

Page 120 of
150
 Page 121 of
150
Another example of descriptive analytics that may be familiar to you is
financial statement analysis. Financial statements are periodic reports that
detail financial information about a business and, together, give a holistic
view of a company’s financial health.
There are several types of financial statements, including the balance sheet,
income statement, cash flow statement, and statement of shareholders’ equity.
Each caters to a specific audience and conveys different information about a
company’s finances.
Financial statement analysis can be done in three primary ways: vertical,
horizontal, and ratio.
Vertical analysis involves reading a statement from top to bottom and
comparing each item to those above and below it. This helps determine
relationships between variables. For instance, if each line item is a
percentage of the total, comparing them can provide insight into which are
taking up larger and smaller percentages of the whole.
Horizontal analysis involves reading a statement from left to right and
comparing each item to itself from a previous period. This type of analysis
determines change over time. Finally, ratio analysis involves comparing one
section of a report to another based on their relationships to the whole. This
directly compares items across periods, as well as your company’s ratios to
the industry’s to gauge whether yours is over- or underperforming.
Each of these financial statement analysis methods are examples of
descriptive analytics, as they provide information about trends and
relationships between variables based on current and historical data.
3. Demand Trends
Descriptive analytics can also be used to identify trends in customer
preference and behavior and make assumptions about the demand for
specific products or services. Streaming provider Netflix’s trend
identification provides an excellent use case for descriptive analytics.
Netflix’s team—which has a track record of being heavily data- driven—
gathers data on users’ in-platform behavior. They analyze this data to
determine which TV series and movies are trending at any given time and
Page 121 of
150
 Page 122 of
list trending titles in a section of the platform’s home screen. 150

Not only does this data allow Netflix users to see what’s popular—and thus,
what they might enjoy watching—but it allows the Netflix team to know
which types of media,

Page 122 of
150
 Page 123 of
150
themes, and actors are especially favored at a certain time. This can drive
decision- making about future original content creation, contracts with
existing production companies, marketing, and retargeting campaigns.
4. Aggregated Survey Results
Descriptive analytics is also useful in market research. When it comes time
to glean insights from survey and focus group data, descriptive analytics
can help identify relationships between variables and trends.
For instance, you may conduct a survey and identify that as respondents’
age increases, so does their likelihood to purchase your product. If you’ve
conducted this survey multiple times over several years, descriptive
analytics can tell you if this age- purchase correlation has always existed or
if it was something that only occurred this year.
Insights like this can pave the way for diagnostic analytics to explain why
certain factors are correlated. You can then leverage predictive and
prescriptive analytics to plan future product improvements or marketing
campaigns based on those trends.
5. Progress to Goals
Finally, descriptive analytics can be applied to track progress to goals.
Reporting on progress toward key performance indicators (KPIs) can help
your team understand if efforts are on track or if adjustments need to be
made.
For example, if your organization aims to reach 500,000 monthly unique
page views, you can use traffic data to communicate how you’re tracking
toward it. Perhaps halfway through the month, you’re at 200,000 unique
page views. This would be underperforming because you’d like to be
halfway to your goal at that point—at 250,000 unique page views. This
descriptive analysis of your team’s progress can allow further analysis to
examine what can be done differently to improve traffic numbers and get
back on track to hit your KPI.

USING DATA TO IDENTIFY RELATIONSHIPS AND TRENDS

“Never before has so much data about so many different things been
Page 123 of
150
 Page 124 of
150
collected and stored every second of every day,” says Harvard Business
School Professor Jan Hammond in the online course Business Analytics. “In
this world of big data, data

Page 124 of
150
 Page 125 of
150
literacy—the ability to analyze, interpret, and even question data—is an
increasingly valuable skill.”
Leveraging descriptive analytics to communicate change based on current
and historical data and as a foundation for diagnostic, predictive, and
prescriptive analytics has the potential to take you and your organization
far.
=================================================
==============
(3.2) VISUALIZING AND EXPLORING DESCRIPTIVE DATA

How is data visualization used in descriptive analytics?

Data visualization involves presenting the data visually or graphically to detect
patterns, trends, and correlations that are not usually apparent from the raw data.
The trends and the patterns in the data cannot be recognized and they go
undetected if not in the visual form.

Why are visuals so important with descriptive analytics?

Data visualization gives us a clear idea of what the information means by
giving it visual context through maps or graphs. This makes the data more
natural for the human mind to comprehend and therefore makes it easier
to identify trends, patterns, and outliers within large data sets.

What is data visualization and exploration?

Visualization and Exploration. Make sense of your data. Visualize spatial
patterns, trends, outliers, and anomalies. Generate hypotheses and keep your
analysis moving forward. Explore your data to be sure you're asking the
right questions.

Data visualization and descriptive statistics

Descriptive statistics turn the data into something more understandable than
raw data but data visualization goes further than that and creates a visual which
quickly tells a story. For example, a pie graph shows information much better

Page 125 of
150
 Page 126 of
than a bunch of numbers. 150

Page 126 of
150
 Page 127 of
150
DESCRIPTIVE STATISTICS AND DATA VISUALIZATION
Turn Your Statistics Into Something More Interesting Data is quickly
becoming a defining thing in the business world. It is the lifeblood of every
company decision and thus, it defines what companies do. A company
which doesn’t pay attention to proper statistics can be at a serious
disadvantage from companies who do, especially companies that use
descriptive statistics and data visualization.
Data has to be good if a business wants to remain relevant and successful
in the business world.
The first step would be to collect the data, which is quite easy in many ways.
Then the gathered information needs to be analyzed and understood. But
what comes after that? Simple – descriptive data and data visualization.

Descriptive Statistics
Descriptive statistics describes data – it summarizes and organizes all of
the collected data into something manageable and simple to understand.
The descriptions can include the entire data set or just a part of the data
set.
One of the most important things to know about descriptive data analysis is
that it focuses on the data instead of on the implication that can be far
reaching and go beyond the represented data.
This is the main difference between inferential statistics and descriptive
statistics. Inferential statistics uses complicated calculations to make
predictions while descriptive statistics doesn’t.
This is just the basic information you need to know about descriptive
statistics, but it’s worth understanding the basics before we dive in any
deeper.

Examples of Descriptive Statistics

If you want to understand the role of descriptive analysis, you need to know
some examples of it. The first thing to know here are all of the types of
Page 127 of
150
 Page 128 of
statistical analyses that you could find in real life. 150

 The first one is the central tendency which is represented by the

median, mean, and mode. The mean is the average of the dataset
and the median is the value

Page 128 of
150
 Page 129 of
150
of a data point in the middle of a set while mode is the value which is
more frequent and appears often. One of the common examples of
mean is GPA, for example. The student’s academic success is
measured by the average of their grades.
 The second type is the frequency. This is a measure of how
commonly and frequently something happens. This is often seen in
descriptive statistics when summarizing polls or surveys, and their
responses. For instance, if 46% of people say yes to some questions.
 The third type would be the measure of position, which includes
quartile and percentile ranks. This type of descriptive analysis and
statistics describes different points of data and how they relate to
each other. This is used when comparing the data points against
each other.
 Finally, the fourth type is the variation of dispersion which is
commonly used as a tool to determine the range of values that the
data encompasses and it identifies the maximum and minimum values
as well. The variance of information can also be attained and it helps
determine certain points.

Why is Descriptive Statistics Important?

Descriptive statistics is a vital point of any business strategy. Raw data comes in
the
form of a huge spreadsheet filled with numbers and it’s not often organized
properly. It’s even complex for data experts.
The clutter of numbers is often hard to read and interpret.
Descriptive statistics organizes all of the mess and clutter, making the
information usable. This is the crucial step to do before you embark on the
journey of data visualization.

What Are Descriptive Statistics?

Descriptive statistics are brief descriptive coefficients that summarize a
given data set, which can be either a representation of the entire

Page 129 of
150
 Page 130 of
150
population or a sample of a population. Descriptive statistics are broken
down into measures of central tendency and measures of variability
(spread). Measures of central tendency include the mean,

Page 130 of
150
 Page 131 of
150
median, and mode, while measures of variability include standard
deviation, variance, minimum and maximum variables, kurtosis, and
skewness.
 Descriptive statistics summarizes or describes the characteristics of a data
set.
 Descriptive statistics consists of two basic categories of measures:
measures of central tendency and measures of variability (or spread).
 Measures of central tendency describe the center of a data set.
 Measures of variability or spread describe the dispersion of data within the
set.

Understanding Descriptive Statistics

Descriptive statistics, in short, help describe and understand the features of
a specific data set by giving short summaries about the sample and
measures of the data. The most recognized types of descriptive statistics
are measures of center:
the mean, median, and mode, which are used at almost all levels of math
and statistics. The mean, or the average, is calculated by adding all the
figures within the data set and then dividing by the number of figures within
the set.
For example, the sum of the following data set is 20: (2, 3, 4, 5, 6). The
mean is 4 (20/5). The mode of a data set is the value appearing most often,
and the median is the figure situated in the middle of the data set. It is the
figure separating the higher figures from the lower figures within a data set.
However, there are less common types of descriptive statistics that are still
very important.
People use descriptive statistics to repurpose hard-to-understand
quantitative insights across a large data set into bite-sized descriptions. A
student's grade point average (GPA), for example, provides a good
understanding of descriptive statistics. The idea of a GPA is that it takes data
points from a wide range of exams, classes, and grades, and averages them
together to provide a general understanding of a student's overall academic

Page 131 of
150
 Page 132 of
150
performance. A student's personal GPA reflects their mean academic
performance.

Types of Descriptive Statistics

All descriptive statistics are either measures of central tendency or
measures of variability, also known as measures of dispersion.

Page 132 of
150
 Page 133 of
150
Central Tendency
Measures of central tendency focus on the average or middle values of
data sets, whereas measures of variability focus on the dispersion of data.
These two measures use graphs, tables and general discussions to help
people understand the meaning of the analyzed data.
Measures of central tendency describe the center position of a distribution
for a data set. A person analyzes the frequency of each data point in the
distribution and describes it using the mean, median, or mode, which
measures the most common patterns of the analyzed data set.

Measures of Variability
Measures of variability (or the measures of spread) aid in analyzing how
dispersed the distribution is for a set of data. For example, while the
measures of central tendency may give a person the average of a data set,
it does not describe how the data is distributed within the set.
So while the average of the data maybe 65 out of 100, there can still be
data points at both 1 and 100. Measures of variability help communicate
this by describing the shape and spread of the data set. Range, quartiles,
absolute deviation, and variance are all examples of measures of
variability.
Consider the following data set: 5, 19, 24, 62, 91, 100. The range of that
data set is 95, which is calculated by subtracting the lowest number (5) in
the data set from the highest (100).
Why do we need statistics that simply describe data?
Descriptive statistics are used to describe or summarize the characteristics
of a sample or data set, such as a variable's mean, standard deviation, or
frequency. Inferential statistics can help us understand the collective
properties of the elements of a data sample. Knowing the sample mean,
variance, and distribution of a variable can help us understand the world
around us.

Page 133 of
150
 Page 134 of
150
What are mean and standard deviation?
These are two commonly employed descriptive statistics. Mean is the
average level observed in some piece of data, while standard deviation
describes the variance, or how dispersed the data observed in that
variable is distributed around its mean.

Can descriptive statistics be used to make inference or prediction?

No. While these descriptives help understand data attributes, inferential
statistical techniques—a separate branch of statistics—are required to
understand how variables interact with one another in a data set.

Data Visualization
The term itself essentially means that you should take the data you have
and that you should convert it to a visual form which is simpler to digest
and understand. Instead of looking at numbers or spreadsheets, you can
get a picture which shows you the information.
Descriptive statistics turn the data into something more understandable
than raw data but data visualization goes further than that and creates a
visual which quickly tells a story.
For example, a pie graph shows information much better than a bunch of
numbers. And everyone has seen a pie chart many times already.
Pie graphs are very simple but they are effective when used properly. But there
are also different forms of data visualization like:
 Bar charts
 Line graphs
 Scatter plots
 Diagrams
 Spider charts
And there are many more. This is the ultimate visual aid and it’s a key
ingredient in using the data in a helpful way.

Page 134 of
150
 Page 135 of
150
Why is Data Visualization Important?
From a business perspective, data visualization is crucial. Data scientists
can look at the raw data and see something important, but people who are
not data scientists, which is the majority of the decision making teams in
companies, can’t use raw data. That’s why data visualization is necessary
when you need to get a point across. It makes the data clear,
understandable, and it eliminates the confusing aspects of it. With good data
visualization, you can get a lot of success and open the discussion of what to
do with the data you provide.

Data Visualization and Descriptive Statistics

When you combine descriptive statistics and data visualization, you turn the
data into something valuable for your company. One of the most important
functions of data is to help the business leaders make proper decisions. It
increases the effectiveness and makes decisions more solid.
There are many ways in which you can use them together to benefit a
business. It makes it easy to notice some patterns and identify how
different points are related to each other. Business leaders also like to take
a look at historical trends and how they can use them for the business’s
benefit.
The raw data makes it hard to figure out everything while descriptive statistics
and data visualization makes it very easy to understand, making correlations
clearer.
With these two crucial pieces, businesses can become much more versatile. The
data is visually displayed so that everyone can easily understand and companies
can identify untapped markets.
Then they can determine which pieces of their operations can be more
effective and more productive, improving the performance. They can also
find out how to improve customer experience and get feedback.
They can also prepare for growth or changes in the market, prepare for
downturns, as well as prepare for staying ahead of competition, and they
can handle all opportunities or challenges.
Page 135 of
150
 Page 136 of
150
Raw data would make all of this impossible or hard to figure out but
these two techniques – data visualization and descriptive statistics
– can make it easy.

Page 136 of
150
 Page 137 of
150
“When it comes to data visualization and descriptive statistics, these are
extremely useful to companies of all sizes. Both can help the companies
prepare for all sorts of situations, from bad ones to good ones and they can
make the decision making process a lot easier.
The Proper Tools
To make data effective and useful, companies need a proper data
visualization tool. There are many different data visualization tools that
companies can use. From simple to more complex, it all becomes a matter
of preference for companies.
“Finding the right data visualization tool is extremely important in all cases
as it can make a difference between a good data representation that
actually helps and bad data representation that confuses people.

PRESCRIPTIVE DECISION MODELS

Prescriptive decision models help decision makers identify the best solution.
Optimization-finding values of decision variables that minimize (or
maximize) something such as cost (or profit).
Objective function-the equation that minimizes (or maximizes) the
quantity of interest.
Constraints-limitations or restrictions.
Optimal solution -values of the decision variables at the minimum (or
maximum) point.

EXAMPLE OF PRESCRIPTIVE PRICING MODEL

A firm wishes to determine the best pricing for one of its products in order
to maximize profit.

predictive model:
Sales = -2.9485(price) +
3240.9 Total revenue =
(price)(sales) Cost =
10(Sales) + 5000
Page 137 of
150
Page 138 of
150

Page 138 of
150
 Page 139 of
150
max. Profit
s.t.Sales >= 0
Sales is integer

=================================================
=================
=================================================
=============

(3.3) TYPES OF VARIABLES, DESCRIPTIVE STATISTICS, AND SAMPLE SIZE

WHAT IS A VARIABLE?
To put it in very simple terms, a variable is an entity whose value varies. A
variable is an essential component of any statistical data. It is a feature of a
member of a given sample or population, which is unique, and can differ in
quantity or quantity from another member of the same sample or
population. Variables either are the primary quantities of interest or act as
practical substitutes for the same. The importance of variables is that they
help in operationalization of concepts for data collection.

Variables can be classified into various ways as discussed below.

Quantitative vs qualitative
A variable can collect either qualitative or quantitative data. A variable
differing in quantity is called a quantitative variable (e.g., weight of a group
of patients), whereas a variable differing in quality is called a qualitative
variable (e.g., the Fitzpatrick skin type) Quantitative variables can be either
discrete or continuous
Discrete variables are variables in which no values may be assumed
between the two given values (e.g., number of lesions in each patient in a
sample of patients with urticaria).

Continuous variables, on the other hand, can take any value in between the
two given values (e.g., duration for which the weals last in the same sample
Page 139 of
150
 Page 140 of
of patients with urticaria). 150

Page 140 of
150
 Page 141 of
150
Under the umbrella of qualitative variables, you can have
nominal/categorical variables and ordinal variables
Nominal/categorical variables are, as the name suggests, variables which can
be slotted into different categories (e.g., gender or type of psoriasis).
Ordinal variables or ranked variables are similar to categorical, but can be
put into an order (e.g., a scale for severity of itching).

Dependent and independent variables

In the context of an experimental study, the dependent variable (also called
outcome variable) is directly linked to the primary outcome of the study.
The independent variable (sometime also called explanatory variable) is
something which is not affected by the experiment itself but which can be
manipulated to affect the dependent variable.

Descriptive Statistics
Statistics can be broadly divided into descriptive statistics and inferential
statistics.[3,4] Descriptive statistics give a summary about the sample
being studied without drawing any inferences based on probability theory.
Descriptive statistics can be used to describe a single variable (univariate
analysis) or more than one variable (bivariate/multivariate analysis). In the
case of more than one variable, descriptive statistics can help summarize
relationships between variables using tools such as scatter plots.

DESCRIPTIVE STATISTICS CAN BE BROADLY PUT UNDER TWO CATEGORIES:

 Sorting/grouping and illustration/visual displays
 Summary
statistics. Sorting and
grouping
Sorting and grouping is most commonly done using frequency distribution
tables. For continuous variables, it is generally better to use groups in the
frequency table. Ideally, group sizes should be equal (except in extreme
ends where open groups are used; e.g., age “greater than” or “less than”).
Page 141 of
150
 Page 142 of
150
Summary statistics
The main tools used for summary statistics are broadly grouped into
measures of central tendency (such as mean, median, and mode) and
measures of dispersion or variation (such as range, standard deviation, and
variance).

SAMPLE SIZE
In an ideal study, we should be able to include all units of a particular
population under study, something that is referred to as a census.[5,6] This
would remove the chances of sampling error (difference between the
outcome characteristics in a random sample when compared with the true
population values – something that is virtually unavoidable when you take a
random sample). However, it is obvious that this would not be feasible in
most situations. Hence, we have to study a subset of the population to reach
to our conclusions. This representative subset is a sample and we need to
have sufficient numbers in this sample to make meaningful and accurate
conclusions and reduce the effect of sampling error.

We also need to know that broadly sampling can be divided into two types –
probability sampling and nonprobability sampling.
Examples of probability sampling include methods such as simple random
sampling (each member in a population has an equal chance of being
selected), stratified random sampling (in nonhomogeneous populations, the
population is divided into subgroups – followed be random sampling in each
subgroup), systematic (sampling is based on a systematic technique – e.g.,
every third person is selected for a survey), and cluster sampling (similar to
stratified sampling except that the clusters here are preexisting clusters
unlike stratified sampling where the researcher decides on the stratification
criteria), whereas nonprobability sampling, where every unit in the
population does not have an equal chance of inclusion into the sample,
includes methods such as convenience sampling (e.g., sample selected
based on ease of access) and purposive sampling (where only people who
Page 142 of
150
 Page 143 of
meet specific criteria are included in the sample). 150

An accurate calculation of sample size is an essential aspect of good study design.

It is important to calculate the sample size much in advance, rather than have to
go for post

Page 143 of
150
 Page 144 of
150
hoc analysis. A sample size that is too less may make the study
underpowered, whereas a sample size which is more than necessary might
lead to a wastage of resources.
We will first go through the sample size calculation for a hypothesis-based design
(like a randomized control trial).

The important factors to consider for sample size calculation include study
design, type of statistical test, level of significance, power and effect size,
variance (standard deviation for quantitative data), and expected
proportions in the case of qualitative data. This is based on previous data,
either based on previous studies or based on the clinicians' experience. In
case the study is something being conducted for the first time, a pilot study
might be conducted which helps generate these data for further studies
based on a larger sample size). It is also important to know whether the data
follow a normal distribution or not.
================================================================
(3.4) PROBABILITY DISTRIBUTION FOR DESCRIPTIVE ANALYTICS

Does descriptive analytics have probability distribution?

Often the probability distribution for a quantity is unknown. You may be able to
sample it with finite statistics, however. Basic descriptive statistics is the
procedure of encoding various properties of the distribution in a few
numbers. Median: the point with 50% probability above & 50% below.

What is descriptive probability?

It basically describes how large samples of data look like when they are plotted. It
is sometimes called the “bell curve“ or the “Gaussian curve“. Inferential statistics
and the calculation of probabilities require that a normal distribution is given.

What is the purpose of descriptive statistics?

Descriptive statistics can be useful for two purposes: 1) to provide basic
information about variables in a dataset and 2) to highlight potential
Page 144 of
150
 Page 145 of
relationships between 150

Page 145 of
150
 Page 146 of
150
variables. The three most common descriptive statistics can be displayed
graphically or pictorially and are measures of: Graphical/Pictorial Methods.

Probability
I will just give a brief indroduction of probability.
Before going to the actual definition of Probability let’s look at some
terminologies.
 Experiment: An experiment could be something like — whether it
rains in Delhi on a daily basis or not.
 Outcome: Outcome is the result of a single trial. If it rains today, the
outcome of today’s trial is “it rained”.
 Event: An event is one or more outcomes of an experiment. For the
experiment of whether it rains in Delhi every day the event could be
“it rained” or it didn’t rain.
 Probability: This simply the likelihood of an event. So it there’s a 60%
chance of it raining today, the probability of raining is 0.6.

Bernoulli Trials
An experiment which has exactly two outcomes like coin toss is called Bernoulli
Trials.
Probability distribution of the number of successes in n Bernoulli trials is
known as a Binomial distribution.
Formula for Binomial distribution is given below.

Binomial distribution Formula

Probability Mass Function for Binomial distribution with different probability of
success and 100 random variables.

Page 146 of
150
 Page 147 of
150

Probability Mass Function

Probability distribution of continuous random variable (variable that can
assume any possible value between two points) is known as Probability
Density Function. There will be infinite no. of trials in case of continuous
random variable.

Area under a probability density function gives the probability for the
random variable to be in that range.
If I have a population data and I take random samples of equal size from
the data, the sample means are approximately normally distributed.
Normal Distribution
It basically describes how large samples of data look like when they are plotted. It
is sometimes called the “bell curve“ or the “Gaussian curve“.
Inferential statistics and the calculation of probabilities require that a
normal distribution is given. This basically means, that if your data is not
normally distributed, you need to be very careful what statistical tests you
apply to it since they could lead to wrong conclusions.
Page 147 of
150
 Page 148 of
150
In a perfect normal distribution, each side is an exact mirror of the other. It
should look like the distribution on the picture below:

Normal Distribution
In a normal distribution, the mean, mode and median are all equal and fall
at the same midline point.

Normal Distribution Function

A normal distribution with a mean of 0 and a standard deviation of 1 is called
a standard normal distribution. Area under the standard normal
distribution curve would be 1.

=================================================
===============
Page 148 of
150
 Page 149 of
150
(3.5) ANALYSIS OF DESCRIPTIVE ANALYTICS

How do you analyze descriptive analytics?

Interpret the key results for Descriptive Statistics
1. Step 1: Describe the size of your sample.
2. Step 2: Describe the center of your data.
3. Step 3: Describe the spread of your data.
4. Step 4: Assess the shape and spread of your data distribution.
5. Compare data from different groups.

What techniques are used in descriptive analytics?

Descriptive techniques often include constructing tables of means and
quantiles, measures of dispersion such as variance or standard deviation,
and cross- tabulations or "crosstabs" that can be used to examine many
disparate hypotheses. Those hypotheses are often about observed
differences across subgroups.

How does descriptive analysis work?

Descriptive analytics is focused only on what has already happened in a
business and, unlike other methods of analysis, it is not used to draw
inferences or predictions from its findings. Descriptive analytics is, rather, a
foundational starting point used to inform or prepare data for further analysis
down the line.

Which analysis is related with descriptive analytics?

Descriptive statistics are used to describe the basic features of the data in a
study. They provide simple summaries about the sample and the measures.
Together with simple graphics analysis, they form the basis of virtually every
quantitative analysis of data.

HERE ARE SOME COMMON APPLICATIONS OF DESCRIPTIVE ANALYTICS:

 Summarizing past events such as regional sales, customer attrition,
Page 149 of
150
 Page 150 of
or success of marketing campaigns. 150

 Tabulation of social metrics such as Facebook likes, Tweets, or followers.

 Reporting of general trends like hot travel destinations or news trends.

Page 150 of
150
 Page 151 of
150
As soon as the “volume, velocity, and variety” of big data invades the
limited business data silos, the game changes. Now, powered by the hidden
intelligence of massive amounts of market data, descriptive analytics takes
new meaning. Whenever big data intervenes, vanilla-form descriptive
analytics is combined with the extensive capabilities of prescriptive and
predictive analytics to deliver highly-focused insights into business issues
and accurate future predictions based on past data patterns. Descriptive
analytics mines and prepares the data for use by predictive or prescriptive
analytics. Big data lends a wide context to the “nuggets of information” for
telling the whole story.
People and culture can influence the intelligence gathered from business
analytics. The
Analytics: Don’t Forget the Human Element study conducted jointly by Forbes
Insights and EY interviewed global executives and concluded that:
 Every modern business needs to build its data analytics framework,
where the latest data technologies like big data play a crucial role.
 Data and technology should be made available at every corner of an
enterprise to develop and nurture a widespread data-driven culture.
 If data and analytics are aligned with overall business goals, then
day-to-day business decisions will be more driven by data-driven
insights.
 As people drive businesses, the manpower engaged in data
analytics must be competent and adequately trained to support
enterprise goals.
 A centrally managed team must lead the analytics production and
consumption efforts in the enterprise to bring behavioral change
towards a data culture.
 The concept of data analytics must be spread through both formal
data centers and informal social networks for an inclusive growth.

More Use Cases of Descriptive Analytics

Here are some common applications of descriptive analytics:

Page 151 of
150
 Page 152 of
 150
Summarizing past events such as regional sales, customer attrition,
or success of marketing campaigns.
 Tabulation of social metrics such as Facebook likes, Tweets, or followers.
 Reporting of general trends like hot travel destinations or news trends.
As soon as the “volume, velocity, and variety” of big data invades the
limited business data silos, the game changes. Now, powered by the hidden
intelligence of massive

Page 152 of
150
 Page 153 of
150
amounts of market data, descriptive analytics takes new meaning.
Whenever big data intervenes, vanilla-form descriptive analytics is combined
with the extensive capabilities of prescriptive and predictive analytics to
deliver highly-focused insights into business issues and accurate future
predictions based on past data patterns. Descriptive analytics mines and
prepares the data for use by predictive or prescriptive analytics. Big data
lends a wide context to the “nuggets of information” for telling the whole
story.
People and culture can influence the intelligence gathered from business
analytics. The Analytics: Don’t Forget the Human Element study conducted jointly
by Forbes Insights and EY interviewed global executives and concluded that:
 Every modern business needs to build its data analytics framework,
where the latest data technologies like big data play a crucial role.
 Data and technology should be made available at every corner of an
enterprise to develop and nurture a widespread data-driven culture.
 If data and analytics are aligned with overall business goals, then
day-to-day business decisions will be more driven by data-driven
insights.
 As people drive businesses, the manpower engaged in data
analytics must be competent and adequately trained to support
enterprise goals.
 A centrally managed team must lead the analytics production and
consumption efforts in the enterprise to bring behavioral change
towards a data culture.
 The concept of data analytics must be spread through both formal
data centers and informal social networks for an inclusive growth.

Descriptive Analytics: Industry Applications

It is believed by many market experts that US retail (40%) industry and
GPS-based services (60%) are still showing rapid adoption of descriptive
analytics to track teams, customers, and assets across locations to capture
enhanced insights for operational efficiency. McKinsey also claimed that in
Page 153 of
150
 Page 154 of
150
today’s business climate, the three most critical barriers to data analytics
are lack of organizational strategy, lack of involved management, and lack
of available talent. Another Report suggests that descriptive analytics has
made great strides in supply chain mapping (SCM), manufacturing plant
sensors, and GPS vehicle tracking, to gather, organize, and view past
events.

Page 154 of
150
 Page 155 of
150

The Five Steps to analyse Descriptive Analytics

Here are the five sequential steps of descriptive analytics, which should be
followed to get the best results:
Step 1 – State the Business Metrics: Any business, attempting to use
descriptive analytics for business gains, must identify and define the key
performance indicators (KPIs), also known as “metrics,” that will be
generated through the analytics process. The KPIs are usually tied to the
business goals of the company or the business goals of each functional unit
within a company. For example, the company’s finance department may
choose to monitor daily sales, weekly sales, holiday sales, and other metrics
related to time spent on customer payment collections.
Step 2 – Identify the Data Required: The next step is locating the data
required to generate the pre-determined metrics. This step can be complex
as relevant data may be scattered across applications and files. On can
hope that with today’s digitized business processes, it will be easy to track
down and extract that necessary data from multiple locations. Additionally,
data may have to be pulled in from an external source like a e-commerce
websites.
Step 3 – Extract and Prepare the Data: When data resides on multiple
locations, this step can be tedious and time consuming. The data has to be
first extracted and collected on a single repository, then combined and
finally prepared for descriptive analytics. The data may also require
“cleansing” to remove errors and inconsistencies. In today’s AI- and ML-
driven business analytics ecosystem, a process called Data Modeling is
used to prepare and organize the company’s information for further
analytics.
Step 4 – Analyze the Data: Companies usually apply a vast range of tools for
conducting descriptive analytics, ranging from spreadsheets to advanced
business intelligence (BI) software. Descriptive analytics involves
performing mathematical operations on some variables to get the desired
results.
Page 155 of
150
 Page 156 of
150 all the
Step 5 – Present the Data: Once the business analysts have completed
prior steps of descriptive analytics, the fifth and last step is generating the
reports. The reports must be presented in a format that is easily
understood by the intended audience of the reports, which may include a
broad range of business users from

Page 156 of
150
 Page 157 of
150
finance specialists to C-Suite executives. Stunning, visual dashboards
always help to disseminate complex business information. A judicious
combination of graphs, charts, and other visual elements presented on
dashboards may be the best answer to catch the attention of varied
audience.

Does Descriptive Analytics Have Any Disadvantage?

The main disadvantage of descriptive analytics is that it only reports what
has happened in the past or what is happening now without explaining the
root causes behind the observed behaviors or without predicting what is
about to happen in the future. The analysis is generally limited to few
variables and their relationships. However, descriptive analytics becomes a
powerful business resource when it is combined with other types of analytics
for assessing business performance. While descriptive analytics focuses on
reporting past or current events, the other types of analytics explore the root
causes behind observed trends and can also predict future outcomes based
on historical data analysis. Nowadays, ML techniques are used for automated
trends and pattern identification

The Role of Descriptive Analytics in Future Data Analysis

As data-driven businesses continue to use the results from descriptive
analytics to optimize their supply chains and enhance their decision-making
powers, data analytics will move further away from predictive analytics
toward prescriptive analytics or rather towards a “mash-up of predictions,
simulations, and optimization.”
The future of data analytics lies in not only describing what has happened,
but in accurately predicting what might happen in the future. For example, a
GPS navigation system, where descriptive analytics is used to provide
directional cues. However, such analysis is reinforced by “predictive
analytics” offering important details about the journey like the time duration.
Now, if the GPS system is further powered by prescriptive analytics, then the
navigation system will not only provide directions and time, but also the
Page 157 of
150
 Page 158 of
150
quickest way to reach the destination. The best part of such a super-charged
navigation system is that it can even compare several traveling routes and
recommend the best solution.

Page 158 of
150
 Page 159 of
150
As data mining and machine learning jointly offer solutions to predict
customer segments and marketing ROIs, the future predictive analytics
techniques will continue to evolve into Prescriptive Analytics, creating a
mash-up of “predictions, simulations, and optimization.”

==================================================================
==============================================================
UNIT IV
PREDICTIVE ANALYTICS
(Introduction to Predictive analytics - Logic and Data Driven Models -
Predictive Analysis Modeling and procedure - Data Mining for Predictive
analytics. Analysis of Predictive analytics)

What is meant by predictive analytics?

Predictive analytics is a branch of advanced analytics that makes predictions
about FUTURE OUTCOMES using historical data combined with statistical
modeling, data mining techniques and machine learning. Companies employ
predictive analytics to find patterns in this data to identify risks and
opportunities.
Predictive analytics has been defined as the use of data, statistical algorithms,
and machine learning techniques "to analyze current and historical facts to make
predictions about future or otherwise unknown events." The key assumption in
this definition is the idea of using known historical and current data points
to PREDICT THE FUTURE.

How do I start predictive analytics?

Getting Started with Predictive Analytics in 5 Easy Steps
1. 1 Predictive Analytics Getting Easier.
2. 2 Pin Down What You Want to Predict.
3. 3 Choose Right Predictive Analytics Software.
4. 4 Find the Right Data.
5. 5 Prepare Data and Derive a Predictive Analytics Model.
Page 159 of
150
 Page 160 of
6. 6 Put Process in Place for Using Predictive Analytics Model. 150

Page 160 of
150
 Page 161 of
150

What is predictive analytics with examples?

Predictive analytics models may be able to identify correlations between
sensor readings. For example, if the temperature reading on a machine
correlates to the length of time it runs on high power, those two combined
readings may put the machine at risk of downtime. Predict future state
using sensor values.

What is the importance of predictive analytics?

Predictive analytics are used to determine customer responses or purchases,
as well as promote cross-sell opportunities. Predictive models help
businesses attract, retain and grow their most profitable customers. Improving
operations. Many companies use predictive models to forecast inventory and
manage resources.

How do you develop a predictive model?

The steps are:
1. Clean the data by removing outliers and treating missing data.
2. Identify a parametric or nonparametric predictive modeling approach to use.
3. Preprocess the data into a form suitable for the chosen modeling algorithm.
4. Specify a subset of the data to be used for training the model.

Which of the following techniques is used in predictive analytics?

There are three common techniques used in predictive analytics: Decision
trees, neural networks, and regression. Read more about each of these
below.

THE SIX STEPS OF THE PREDICTIVE ANALYTICS PROCESS

There are many predictive analytics techniques out there. I'm not going to
cover them in detail; you can easily get an overview by googling for them.
Instead, I think it's more valuable to cover the core steps of the analytics
process. That way, when you find out more about the specific techniques,
Page 161 of
150
 Page 162 of
your knowledge of the core steps will help you frame your thinking.150
The six steps of the predictive analytics process are:
1. Defining the Project

Page 162 of
150
 Page 163 of
150
2. Collecting the Data
3. Performing the Analysis
4. Modeling
5. Deploying the Model
6. Continuous Model Monitoring
Step 1: Defining the Project
We define the project in terms of outcomes, deliverables, scope of work, and
even data sets. We ask ourselves: what is it that we want to predict? What
degree of accuracy must we achieve to consider the project a success?
What are the data sets we need to have in order to perform the analysis?
Step 2: Collecting the Data
Remember the first diagram contrasting engineering tasks with analytics
tasks? When we collect the data, we are in the engineering phase of the
project. We may even need to build additional automation to make the
collection, cleaning, and preparation of the data easier and faster. This may
be grunt work, but it's crucial grunt work. Garbage in, garbage out, as the
saying goes. You want to ensure the data you prepare is good enough at
this stage.
Step 3: Performing the Analysis
Now, we perform analysis on the sanitized data. The objective here is to
derive several candidate models we may use for prediction. This step is
usually done in tandem with the next step, which is creating the model
itself. In this step, we frequently employ statistical methods specific for
analysis. Plenty of testing is done here as well. We want to validate the
assumptions and test them using standard statistical techniques.
Step 4: Modeling
In this step, we use various statistical and machine learning approaches to
generate a predictive model. We take several candidate models from the
previous step and iteratively train them using training data. When the model
completes the training set, we then test it on new data to see how well it
performs. We may further refine the models or even discard some of them
altogether depending on the testing results. We may also revert to earlier
Page 163 of
150
 Page 164 of
150
stages in order to generate more models, especially if we are not getting the
level of accuracy we are looking for.
Step 5: Deploying the Model

Page 164 of
150
 Page 165 of
150
Eventually, we'll arrive at a predictive model we are willing to go live with.
Now, we deploy it in real-life systems. At this stage, we are back to doing
more engineering tasks. We want to deploy the new model in such a way
that we can collect more data on its performance. Perhaps the model needs
to incorporate new data points as they arrive for maximum effectiveness; in
this case, more engineering is required to ensure this feature is properly
implemented.
Step 6: Continuous Model Monitoring
Our predictive model has gone live. We are collecting data on how it's
performing in real time. Since we will need to regularly tweak the model as
time goes by, we need to continuously monitor the model and its
effectiveness. Deciding on how much to tweak the model is more art than
science. It can be hard to perform analysis in real time, so your data
engineers and your data analysts need to work more closely here.

What is Predictive Analytics?

Predictive Analytics is the domain that deals with the various aspects of
statistical techniques including predictive modeling, data mining,
machine learning, analyzing current and historical data to make the
predictions for the future.

Understanding Predictive Analytics

Predictive Analytics has been developed in the last 50 years and today we
are seeing a huge jump in the number of companies that are using Predictive
Analytics. Today due to the incessant growth of big data and the need to
make data-driven decisions, it is imperative on each and every organization
to make use of Predictive Analytics.
Predictive modeling based techniques help to work in a streamlined fashion
and get the results delivered as per the specific framework.

Page 165 of
150
 Page 166 of
150
The process of Predictive Analytics includes the following steps :

Defining the project : This is the first step of the Predictive Analytics model.
Here you will have a clear-cut definition of the outcome of the project, the
business objectives, the scope of the effort, identifying data sets and more.
Collecting the data : This is the second step of the process wherein you will be
mining for the data from multiple sources and prepare the Predictive
Analytics mode and provide a complete overview of the entire process.
Analyzing the data : This is the process that includes the various steps of
inspection, cleaning, modelling of the data for discovering the objective and
help to reach at a conclusion.
Deploying the statistics : Here you will be working on validating the assumptions
and hypothesis and testing it using the standard statistical models.
Data Modeling : This is the process that provides the ability to create
automatic predictive models of the future. You can also create a set of
models and choose the most optimal one.
Model Deployment : This is the step in which you will be deploying the
analytical results into your everyday business operations helping to get
results, reports and the output of the automated decisions.
Monitoring the Model : The models are reviewed in order to ensure the
performance of it is going in the right direction.
The Predictive models are the relation between the specific performance of
a unit in the sample and other attributes in the unit. The model is designed
in order to understand the possibility of a different sample that exhibits the
same specific performance. It is
Page 166 of
150
 Page 167 of
150
used in many domains for the purpose of answering a whole set of questions
in various areas like marketing, sales, customer service among other
domains.
Predictive Analytics is used for various purposes like business
segmentation, decision- making and other purposes like statistical
techniques among other tasks. There is a huge advancement in the speeds
at which computing is done, the availability of modeling techniques to come
up with valuable insights.

What can you do with Predictive Analytics?

“For predictive analytics, we need an infrastructure that’s much more responsive
to human-scale interactivity: What’s happening today that may influence what
happens tomorrow? A lot of iteration needs to occur on a continual basis for the
system to get smart, for the machine to “learn” – Peter Levine, VC and General
Partner at Andreessen Horowitz,

It is up to every individual organization to find out newer ways to deploy

Predictive Analytics and uncovering of new opportunities in their pursuit of
growth and revenues: Targeted marketing campaigns – A data-driven
approach to customizing the marketing campaigns, understanding
customer response, designing the most appropriate approach to creating
the right marketing campaign, measuring the key performance indicators
and ensuring the campaigns are able to meet the business goals.
Improving operational efficiency – Streamlining the various operations of an
organization, managing the supply chain, inventory management, deploying
the right resources, promoting opportunities for cross-selling, optimizing the
various processes. Risk mitigation – Predictive Analytics deployment for
finding out more about the customer’s aversion to buying a product, the
various factors which dissuade a customer from making the purchase
decisions and finding out how to reduce the risks involved.
Fraud detection – Working with the various analytical tools to find out more
about the pattern detection of the fraud transaction in banking and
Page 167 of
150
 Page 168 of
150
financial domains, preventing the criminal motives, deploying behavioral
analytics to preclude fraud, researching about zero-day vulnerabilities and
reducing the risks of advanced frauds.

Page 168 of
150
 Page 169 of
150
INDUSTRIES USING PREDICTIVE ANALYTICS MODEL
Aerospace : The amount of data that is generated in the modern era
aircrafts is phenomenal. Today due to the abundance of sensors, newer
ways of storing the data and finding various ways in which that data can be
useful, Predictive Analytics is suddenly taking a huge stride in the
aerospace industry.
Automotive : Today’s automobiles are heavily invested when it comes to
deploying the most cutting-edge gadgets, technologies, sensors for coming
up with highly valuable analytical methods for ensuring the driving
experience is simply phenomenal. In the not so distant future, most of the
automobiles will be connected to the internet of things and due to this the
role of Predictive Analytics will only grow stronger.
Energy & Utilities : This is another domain wherein the role of Predictive
Analytics is again very significant. It helps to predict the demand and supply
of electrical energy through the power grids. There are various sophisticated
models that are used for monitoring the plant availability, impact of
changing weather pattern, learning from historical trends, forecasting the
optimal demand and supply balance among other things that can help the
energy domain save huge amounts of money and resources. Banking and
Financial Services : This is one of the biggest domains that is currently
deploying Predictive Analytics at scale. Due to the large amounts of data
being generated and the extremely high stakes involved, banking and
financial institutions are increasingly deploying Predictive Analytics for
ensuring the customers get a world-class experience that is customer-
friendly, secure and forward-looking. It is possible to tailor- make products
and services depending on the profile built around the customer,
opportunities for cross-selling and up-selling, find patterns of fraud and
malpractices among a host of other things.
Retail : The retail industry is working with predictive analytical tools and
technologies to get inside the mind of the customers. It includes the process
of stocking the right products, promoting the right products to the right
customers, providing the most optimal discounts to persuade sales, having
Page 169 of
150
 Page 170 of
150of other
the right strategy for marketing and advertising among a whole host
aspects.
Oil & Gas : The industry of oil and gas is a big user of the domain of
Predictive Analytics. it helps to save millions of dollars through better
predicting equipment failure, need for future resources, ensuring safety and
reliability measures are met, and so on.

Page 170 of
150
 Page 171 of
150
There are a lot of sensor data that needs to be monitored in order to take
the right data- driven decision in the oil and gas industry.
Governments : Since the data in a government department is humungous
thanks to the all-encompassing nature of this domain, there is a huge
untapped opportunity which can be aptly exploited using the right Predictive
Analytics tools and technologies. It could be deployed for providing the right
services to the citizens, monitoring the various welfare schemes are
reaching the right audience, checking corruption and malpractices and so
on.
Manufacturing : Even in today’s world of services-oriented economy the
domain of manufacturing is still extremely important. The manufacturing
industry can make use of Predictive Analytics in order to streamline the
various processes, improve the quality of service, supply chain
management, optimizing distribution and such other tasks for enhancing the
overall business revenue and achieve bigger goals.

Advantages of Predictive Analytics

Organizations are increasingly working on directing, optimizing and
automating the decisions for improving the business processes. Here are
some of the advantages of Predictive Analytics framework:
 Deploying analytics for analyzing past, present and projected future
outcome
 Choosing the right step to drive the action in the most optimal manner
 Predictive Analytics includes both decision optimization and advanced
analytics
 Supporting action and recommended actions are sent to the decision-
makers
 It helps to take proactive risk management measures
 Testing iterative actions for the intended and unintended consequences
 Process improvement, cost reduction and revenue generation are all
possible

===============================================================

Page 171 of
150
 Page 172 of
150
(4.2) PREDICTIVE ANALYSIS - LOGIC AND DATA DRIVEN MODELS

PREDICTIVE MODELING
What is predictive modeling?
Predictive modeling is a mathematical process used to predict future
events or outcomes by analyzing patterns in a given set of input data. It is
a crucial component
of predictive analytics, a type of data analytics which uses current and historical
data to forecast activity, behavior and trends.
Examples of predictive modeling include estimating the quality of a sales
lead, the likelihood of spam or the probability someone will click a link or
buy a product. These capabilities are often baked into various business
applications, so it is worth understanding the mechanics of predictive
modeling to troubleshoot and improve performance.

Although predictive modeling implies a focus on forecasting the future, it

can also predict outcomes (e.g., the probability a transaction is fraudulent).
In this case, the event has already happened (fraud committed). The goal
here is to predict whether future analysis will find the transaction is
fraudulent. Predictive modeling can also forecast future requirements or
facilitate what-if analysis.
"Predictive modeling is a form of data mining that analyzes historical data
with the goal of identifying trends or patterns and then using those insights
to predict future outcomes," explained Donncha Carroll a partner in the
revenue growth practice of Axiom Consulting Partners. "Essentially, it asks
the question, 'have I seen this before' followed by, 'what typically comes
after this pattern.'"

TYPES OF PREDICTIVE MODELS

There are many ways of classifying predictive models and in practice
multiple types of models may be combined for best results. The most
salient distinction is
Page 172 of
150
 Page 173 of
between unsupervised versus supervised models. 150
 Unsupervised models use traditional statistics to classify the data
directly, using techniques like logistic regression, time series analysis
and decision trees.

Page 173 of
150
 Page 174 of
150
 Supervised models use newer machine learning techniques such
as neural networks to identify patterns buried in data that has
already been labeled.
The biggest difference between these approaches is that with supervised
models more care must be taken to properly label data sets upfront.
"The application of different types of models tends to be more domain-
specific than industry-specific," said Scott Buchholz, government and
public services CTO and emerging technology research director at
Deloitte Consulting.
In certain cases, for example, standard statistical regression analysis may
provide the best predictive power. In other cases, more sophisticated
models are the right approach. For example, in a hospital, classic statistical
techniques may be enough to identify key constraints for scheduling, but
neural networks, a type of deep learning, may be required to optimize
patient assignment to doctors.
Once data scientists gather this sample data, they must select the right
model. Linear regressions are among the simplest types of predictive
models. Linear models take two variables that are correlated -- one
independent and the other dependent -- and plot one on the x-axis and one
on the y-axis. The model applies a best fit line to the resulting data points.
Data scientists can use this to predict future occurrences of the dependent
variable.

SOME OF THE MOST POPULAR METHODS INCLUDE THE FOLLOWING:

 Decision trees. Decision tree algorithms take data (mined, open
source, internal) and graph it out in branches to display the possible
outcomes of various decisions. Decision trees classify response
variables and predict response variables based on past decisions, can
be used with incomplete data sets and are easily explainable and
accessible for novice data scientists.
 Time series analysis. This is a technique for the prediction of events
through a sequence of time. You can predict future events by
Page 174 of
150
 Page 175 of
analyzing past trends and extrapolating from there. 150

 Logistic regression. This method is a statistical analysis method that

aids in data preparation. As more data is brought in, the algorithm's
ability to sort and classify it improves and therefore predictions can
be made.

Page 175 of
150
 Page 176 of
150
 Neural networks. This technique reviews large volumes of labeled
data in search of correlations between variables in the data. Neural
networks form the basis of many of today's examples of artificial
intelligence (AI), including image recognition, smart assistants and
natural language generation.
The most complex area of predictive modeling is the neural network. This
type of machine learning model independently reviews large volumes of
labeled data in search of correlations between variables in the data. It can
detect even subtle correlations that only emerge after reviewing millions of
data points. The algorithm can then make inferences about unlabeled data
files that are similar in type to the data set it trained on.

Common algorithms for predictive modeling

 Random Forest. This algorithm combines unrelated decision trees
and uses classification and regression to organize and label vast
amounts of data.
 Gradient boosted model. Similar to Random Forest, this algorithm uses
several decision trees, but in this method, each tree corrects the flaws
of the previous one and builds a more accurate picture.
 K-Means. This algorithm groups data points in a similar fashion as
clustering models and is popular in devising personalized retail offers.
It create personalized offers by seeking out similarities among large
groups of customers.
 Prophet. A forecasting procedure, this algorithm is especially effective
when dealing with capacity planning. This algorithm deals with time
Page 176 of
150
 Page 177 of
series data and is relatively flexible. 150

Page 177 of
150
 Page 178 of
150
BENEFITS OF PREDICTIVE MODELING
Phil Cooper, group VP of products at Clari, a RevOps software startup, said
some of the top benefits of predictive modeling in business include the
following:
 Prioritizing resources. Predictive modeling is used to identify sales lead
conversion and send the best leads to inside sales teams; predict
whether a customer service case will be escalated and triage and
route it appropriately; and predict whether a customer will pay their
invoice on time and optimize accounts receivable workflows.
 Improving profit margins. Predictive modeling is used to forecast
inventory, create pricing strategies, predict the number of
customers and configure store layouts to maximize sales.
 Optimizing marketing campaigns. Predictive modeling is used to
unearth new customer insights and predict behaviors based on
inputs, allowing organizations to tailor marketing strategies, retain
valuable customers and take advantage of cross-sell opportunities.
 Reducing risk. Predictive analytics can detect activities that are out
of the ordinary such as fraudulent transactions, corporate spying or
cyber attacks to reduce reaction time and negative consequences.
The techniques used in predictive modeling are probabilistic as opposed
to deterministic. This means models generate probabilities of an
outcome and include some uncertainty.
"This is a fundamental and inherent difference between data modeling of
historical facts versus predicting future events [based on historical data] and
has implications for how this information is communicated to users," Cooper
said. Understanding this difference is a critical necessity for transparency
and explainability in how a prediction or recommendation was generated.

PREDICTIVE MODELING TOOLS

Before deploying a predictive model tool, it is crucial for your organization
to ask questions and sort out the following: Clarify who will be running the
software, what the use case will be for these tools, what other tools will
Page 178 of
150
 Page 179 of
150
your predictive analytics be interacting with, as well as the budget.

Page 179 of
150
 Page 180 of
150
Different tools have different data literacy requirements, are effective in
different use cases, are best used with similar software and can be
expensive. Once your organization has clarity on these issues, comparing
tools becomes easier.

 Sisense. A business intelligence software aimed at a variety of

companies that offers a range of business analytics features. This
requires minimal IT background.
 Oracle Crystal Ball. A spreadsheet-based application focused on
engineers, strategic planners and scientists across industries that can
be used for predictive modeling, forecasting as well as simulation and
optimization.
 IBM SPSS Predictive Analytics Enterprise. A business intelligence
platform that supports open source integration and features
descriptive and predictive analysis as well as data preparation.
 SAS Advanced Analytics. A program that offers algorithms that
identify the likelihood of future outcomes and can be used for data
mining, forecasting and econometrics.

THE FUTURE OF PREDICTIVE MODELING

There are three key trends that will drive the future of data modeling.
1. First, data modeling capabilities are being baked into more business
applications and citizen data science tools. These capabilities can
provide the appropriate guardrails and templates for business users to
work with predictive modeling.
2. Second, the tools and frameworks for low-code predictive modeling
are making it easier for data science experts to quickly cleanse data,
create models and vet the results.
3. Third, better tools are coming to automate many of the data
engineering tasks required to push predictive models into production.
Carroll predicts this will allow more organizations to shift from simply
building models to deploying them in ways that deliver on their
Page 180 of
150
 Page 181 of
potential value. 150
===============================================================

Page 181 of
150
 Page 182 of
150
(4.3) DATA MINING FOR PREDICTIVE ANALYTICS

What is the difference between data mining and predictive analytics?

Data mining is the process of discovering useful patterns and trends in large
data sets. Predictive analytics is the process of extracting information from
large datasets in order to make predictions and estimates about future
outcomes.

Data mining is the process of finding anomalies, patterns and correlations

within large data sets to predict outcomes. Using a broad range of techniques,
you can use this information to increase revenues, cut costs, improve
customer relationships, reduce risks and more.

How do data mining and predictive analytics work?

Done right, data mining gives users a clear picture of what's going on.
Predictive analytics uses the information that surfaced during the data
mining process to predict future outcomes, model different scenarios, and
identify the best strategy for any given situation.

Why data mining is important in predictive analytics?

Data mining is used to provide two primary advantages: to give
businesses the predictive power to estimate the unknown or future values
and to provide businesses the descriptive power by finding interesting
patterns in the data. Predictive analytics are used to collect and predict
future results and trends.

DATA MINING
Data mining is the process of discovering patterns and anomalies form large
sets of data through the application of statistics, machine learning and
database systems [17]. The objective of data mining is to extract the useful
data from data set and process them to obtain information that has an
Page 182 of
150
 Page 183 of
understandable structure. It includes provision for automated and150
semi-
automated analysis of large quantities of data set to extract recognizable
patterns, dependencies between the data, groups or clusters of records

Page 183 of
150
 Page 184 of
150
and the relation between these records as well as the anomalies occurring
within the system. Data mining could be applied to identify multiple groups
and clusters of data and forward them for further analysis through machine
learning or predictive analytics.

Data mining commonly involves the following 6 tasks

1. Anomaly Detection - In data mining, anomaly detection is the detection
of events, items or observations that do not conform to a pattern that is
expected or to an established normal behavior
2. Association Rule Learning – This involves discovering and describing the
relationship between the various variables present within the data set. It is
intended to identify and discover extensive rules within the data in the
databases. This information could be useful in undertaking decisions before
forth going any dilemma that could be an integral part of future
perspective of the business of the organization [16].
3. Clustering – Clustering involves identifying similarities between the
various objects of the data set and abstracting them into classes of similar
objects with similar properties. It involves discovering structures and
groups in the data have similar properties or are similar to each other in
distinction, without using the available structures present in the data set.
4. Classification – It includes the process of creating generic or
generalized known structures and properties and apply them to the data
that has been clustered.
5. Regression – It involves development of a function that is responsible for
predicting various properties and factors using regression techniques.
6. Summarization – This task involves and revolves around development of a
compact representation of data set, including generation of report and
visualization.

DATA MINING TECHNIQUES

1. Association – Association is one of the most familiar and most commonly
Page 184 of
150
 Page 185 of
150
known technique of data mining. In association, the similarities between
different objects is identified for recurring patterns and a correlation is
established between the objects. The objects are generally of the same
type so as to define the correlation among them to identify the patterns.
This could be exhibited through an example of a customer who

Page 185 of
150
 Page 186 of
150
always bought chocolates along with milk. The milk in this case gets
associated with chocolates and thus a pattern is emerged that provides
information about the sale of milk and chocolates and it suggests that the
next time the person buys the chocolate, he’ll be buying milk as well.
2. Classification – Classification, as the name suggests is the process of
identifying an object by relating with it, multiple attributes that describe that
object thoroughly. Classification is used to build up the reference or idea of
an object by describing it using multiple attributes to define its particular
class. Let us try to understand the same though an example of classification
of cars. Given a car as an object, we can identify or classify it through
multiple attributes such as shape, number of seats, transition type etc.
Through proper comparison and analysis of the categories or attributes, one
can identify the object to be classified into a similar kind of attribute.
3.Clustering – Once the attributes are applied to an object, through proper
and considerate examination of the attributes or classes, one can identify it
into groups of similar kind of objects. Such group of similar objects is
referred to as a cluster. A cluster uses a single or a group of attributes or
classes defined of an object as its base for segregation and combine a set of
results having correlating group of objects. Clustering works bi-directionally.
It is useful in identifying a group of objects having a set of similar attributes
or classes. Also it is useful in identifying the identification criteria for an
existing cluster of objects.
4.Prediction – Prediction is referred to as a wide area of study that ranges
from predicting about the failure of a machinery to identification of frauds
and intrusions to even predicting the future aspect of the organization or
business. When combined with the techniques of data mining, prediction
involves various tasks such as analysis and creation of trends,
classification, clustering, pattern discovery and relation. Through thorough
examination and analysis over the past trends or events, one can make
effective measurement regarding the future occurrence of that event.
5.Sequential Patterns - Sequential patterns are defined over a long period of
time wherein trends and similar activities or events are identified to be
Page 186 of
150
 Page 187 of
150
occurring on a regular basis [23]. It is considered a very useful technique to
identify the trends and similar events. Considering an example of a
customer at a grocery store who buys a collection of objects regularly over
the year or so. Through analytics over the historical data,

Page 187 of
150
 Page 188 of
150
patterns of grocery bought over the year can be used to provide the
sequential pattern of what is to be added to the grocery list.
6.Decision trees – Decision trees are basically related to the above defined
techniques. They can be either used for providing the criteria for selection or
to provide support to the selection and use of specific data within the overall
structure. A decision tree is started and created through a question that has
more than a single result or option to be selected [14]. Each of the result in
turn leads to another question that it can be categorized into a result set of
more than one option. These subsequent questions leads to the
categorization of the data set so as to facilitate the prediction based on the
result set.
7.Combinations – In real world applications, several techniques are applied in
combination. Exclusive use of a single technique is not valid. Clustering and
combination are similar techniques and are used combined so as to achieve
the desired effective result. Clustering can be used to identify the nearest
neighbors which can be useful in refinement of the classification of the data
set in use. In the same way, decision trees can act as base for the
techniques of sequential patterns and is used to identify and build
classification which when done over a longer period of time can be used to
identify the patterns of similarity between the data set and could help in
prediction.
8.Long Term Processing – Data analytics and predictive analytics is purely
based on the data and information processed over a period of time. There is
a need to record the data for a long term and then process the data for the
patterns, classification, categorization and prediction. For example, for
predictive learning and sequential patterns, there is a need to store and
process the historical data and instances of information for building a
pattern. As the time passes, new data and information is identified and
processed along with the historical data and information and the analytics is
applied on the whole set of data so as to cope with the additional data.

PREDICTIVE ANALYTICS TECHNIQUES

Page 188 of
150
 Page 189 of
150
The techniques or approaches that can be used to conduct predictive
analytics on a data set can be broadly defined and categorized as follows.
1. Regression Analytics

Page 189 of
150
 Page 190 of
150
Regression techniques are focused on establishment of mathematical
equations so as to model, represent and process the information from the
available data set [25]. Some of the regression techniques being in use are
described as follows.
a. Linear Regression Model – This technique establishes a linear relationship
between the dependent variable y and multiple independent variables x. It is
represented through the linear equation y=a+bx+c

b. Logistic Regression – This technique is applied so as to find the

probability regarding the success or failure of an event. This technique
comes to use when the value of the dependent variable is binary.

c.Polynomial Regression – In this technique, the prediction line is not a

Page 190 of
150
 Page 191 of
straight or linear one, but is a curve that fits the points of the data150
set
being predicted upon.

Page 191 of
150
 Page 192 of
150

d.Stepwise Regression – This technique comes into play when there is a

presence of multiple independent factors or variables. The best fit is
predicted through stepwise incremental addition or removal of predictor
variables as required for each of the step. This technique has the aim of
achieving the maximum prediction power with the use of minimal number of
predictor variables.
e.Ridge Regression – Ridge regression technique is used where there is a
multi- collinearity that is the data set has multiple independent variables
with high extent or correlation. The ridge regression technique can be
represented through the equation y = a + b1x1 + b2x2 + b3x3 +…+ e
f.Lasso Regression – Lasso regression is highly similar to ridge regression
technique with less variance coefficients and high accuracy of the linear
regression models. In this technique, variables having high correlation, only
of the predictor variables is picked while all others are shirked to zero.
g.Elastic net Regression – This technique is a combination of Ridge
Regression technique and Lasso Regression technique. It enhances the
accuracy of the best fit result and provides the advantage of no
limitations over the number of variables selected and has the ability to
suffer and withhold double shrinkage.
2. Machine Learning Analytics
Page 192 of
150
 Page 193 of
Machine learning is a branch of AI (Artificial Intelligence) that was 150
devised to
provide the ability to computers to learn. These days, it is being used in
various statistical models

Page 193 of
150
 Page 194 of
150
and methods for prediction of risks and opportunities and is found
applicable in various fields such as banking fraud detection, medical
diagnosis, natural language processing and analysis over the stock market.
Some of the methods commonly used for predictive analytics through
machine learning are defined as follows.
a. Neural Networks – These are nonlinear modelling techniques wherein they
learn the relationship between the inputs and the outputs through training.
There are 3 types of trainings used by neural networks: supervised,
unsupervised and reinforcement training. This technique can be applied for
prediction, control and classification in various fields.
b. Multilayer perceptron – This technique consists of an output and an input
layer with multiple hidden layers of nonlinear weights and is determined and
defined through the weight factors by adjusting the weight of the network.
The adjustment of the weights is done through a process called training the
nets that contains the learning rules.
c. Radial basis functions – Radial basis function technique is built on the
criteria of distance of data set with reference to the center. These functions
are basically used for interpolation of data as well as smoothening of data.
d. Support vector machines – SVMs are designed and defined to detect and
identify the complex patterns and sequences within the data set through
clustering and classification of the data. They are also referred to as the
learning machines.
e. Naïve Bayes – Naïve Bayes is deployed for the execution of classification
of data through the application of Bayes Conditional Probability [8]. It is
basically implemented and applied when the number of predictors is very
high.
f. k-nearest neighbours – This techniques involves pattern recognition
techniques of statistical prediction. It consists of a training set with both
positive and negative values.
g. Geospatial Predictive Modelling – This modelling technique involves
presence of occurrence of events over a spatial area with influence of
special environmental factors. The occurrence of events is defined to be
Page 194 of
150
 Page 195 of
neither uniform not random but special in nature. 150

APPLICATIONS OF PREDICTIVE ANALYSIS THROUGH DATA MINING

1. Customer Relationship Management (CRM) – Analytical CRM is one of the
most frequently used application of predictive analytics these days. The
predictive analytics under this area is applied to the customer data to
pursue and attain the CRM objectives

Page 195 of
150
 Page 196 of
150
defined for an organization. CRM makes use of these analysis in applications
for increasing the sales targets, marketing and campaigns [2][5]. This not
only impacts the business growth, but also makes the business customer
eccentric through widening the base for customer satisfaction [7].
2. Child Protection – Child abuse is a serious offence and child protection is
most sought after within any country [18]. Several child welfare
organizations have applied the predictive analytics to flag high risk cases of
child abuse [11]. The predictive models help in identifying from medical
records, the cases that could fall under the child abuse criteria. This
approach is termed as “innovative” by the Commission to Eliminate Child
Abuse and Neglect Fatalities (CECANF) [19]. Using the predictive analytics,
the child abuse related felonies have been identified at the earlier stage
preventing from much further harm [20].
3. Clinical decision support systems – As defined, Clinical decision support
(CDS) provides clinicians, staff, patients, or other individuals with knowledge
and person- specific information, intelligently filtered or presented at
appropriate times, to enhance health and health care [10][21]. It
encompasses a variety of tools and interventions such as computerized
alerts and reminders, clinical guidelines, order sets, patient data reports and
dashboards, documentation templates, diagnostic support, and clinical
workflow tools. [22] Experts have involved the predictive analytics to model
the clinical data of patients so as determine the extent to which a patient
might be exposed to a disease and predict the risk of development of certain
conditions such as heart disease, asthma or diabetes. These approaches
have been devised so as to predict both the state and level of the disease as
well as the diagnosis and disease progression forecasting [12][13].
4. Collection Analytics – Many portfolios these days has a set of customer
who doesn’t make their payment within the defined time and the companies
put up a lot of financial expenditure on collection of those payments [27].
Thus the companies have started applying the predictive analytics over their
customers for effective analysis of the spending, usage and behavior of the
customer who are unable to make the payment and allocate the most
Page 196 of
150
 Page 197 of
150
effective legal agencies and strategies for each customer, thus increasing
recovery significantly with lesser financial expenditure.

Page 197 of
150
 Page 198 of
150
5. Fraud Detection – Fraud is one of the biggest challenges faced by
businesses around the globe and can be of various kinds such as fraudulent
online transactions, invalid credits [15], identity thefts and multiple false
insurance claims. Predictive modelling can be applied to this area so as to
model the data of the organization and detect such fraudulent activities
[24]. These models have the capabilities to identify and predict the
customers engaged in such activities. Many revenue systems too take in this
consideration to mine out the non-tax payers and identify tax fraud [24].
6. Project Risk Management – Each company employs a risk management
technique so as to increase their revenue. These risk management
techniques involves the use of predictive analytics to predict the cost and
benefit of a project within an organization and also helps organizing the work
management so as to maximize the profit statement. These approaches can
be applied ranging from projects to markets so as to maximize the return
from the investment.

CONCLUSIONS
Predictive analytics is the future of Data Mining. This survey provided with
the trends, techniques and applications of Predictive analytics through the
application of data mining. Data Mining leading to predictive analytics is
becoming key to every organization as it can be applied under various
circumstances so as to highlight growth of the organization. Predictive
Analytics aid not only in expansion of the business, but also prevents the
degradation through analysis of the fraudulent activities.
================================================================
(4.4) ANALYSIS OF PREDICTIVE ANALYTICS
What Is Predictive Analytics?
The term predictive analytics refers to the use of statistics and modeling
techniques to make predictions about future outcomes and performance.
Predictive analytics looks at current and historical data patterns to
determine if those patterns are likely to emerge again. This allows
businesses and investors to adjust where they use their resources to take
Page 198 of
150
 Page 199 of
150used to
advantage of possible future events. Predictive analysis can also be
improve operational efficiencies and reduce risk.

Page 199 of
150
 Page 200 of
150
PREDICTIVE ANALYTICS IS A DECISION-MAKING TOOL
IN A VARIETY OF INDUSTRIES.
1. Forecasting
Forecasting is essential in manufacturing because it ensures the optimal
utilization of resources in a supply chain. Critical spokes of the supply
chain wheel, whether it is inventory management or the shop floor,
require accurate forecasts for functioning.
Predictive modeling is often used to clean and optimize the quality of data
used for such forecasts. Modeling ensures that more data can be ingested by
the system, including from customer-facing operations, to ensure a more
accurate forecast.
Forecasting
Forecasting is essential in manufacturing because it ensures the optimal
utilization of resources in a supply chain. Critical spokes of the supply
chain wheel, whether it is inventory management or the shop floor,
require accurate forecasts for functioning.
Predictive modeling is often used to clean and optimize the quality of data
used for such forecasts. Modeling ensures that more data can be ingested by
the system, including from customer-facing operations, to ensure a more
accurate forecast.
2. Credit
Credit scoring makes extensive use of predictive analytics. When a
consumer or business applies for credit, data on the applicant's credit
history and the credit record of borrowers with similar characteristics are
used to predict the risk that the applicant might fail to perform on any credit
extended.
3. Underwriting
Data and predictive analytics play an important role in underwriting.
Insurance companies examine policy applicants to determine the likelihood
of having to pay out for a future claim based on the current risk pool of
similar policyholders, as well as past events that have resulted in payouts.
Predictive models that consider characteristics in comparison to data about
Page 200 of
150
 Page 201 of
150
past policyholders and claims are routinely used by actuaries. 4.Marketing
Individuals who work in this field look at how consumers have reacted to the
overall economy when planning on a new campaign. They can use these
shifts in demographics to determine if the current mix of products will entice
consumers to make a purchase.

Page 201 of
150
 Page 202 of
150
Active traders, meanwhile, look at a variety of metrics based on past events
when deciding whether to buy or sell a security. Moving averages, bands,
and breakpoints are based on historical data and are used to forecast future
price movements.
Credit scoring makes extensive use of predictive analytics. When a
consumer or business applies for credit, data on the applicant's credit
history and the credit record of borrowers with similar characteristics are
used to predict the risk that the applicant might fail to perform on any credit
extended.
5.Underwriting
Data and predictive analytics play an important role in underwriting.
Insurance companies examine policy applicants to determine the likelihood
of having to pay out for a future claim based on the current risk pool of
similar policyholders, as well as past events that have resulted in payouts.
Predictive models that consider characteristics in comparison to data about
past policyholders and claims are routinely used by actuaries. 6.Marketing
Individuals who work in this field look at how consumers have reacted to the
overall economy when planning on a new campaign. They can use these
shifts in demographics to determine if the current mix of products will entice
consumers to make a purchase.
Active traders, meanwhile, look at a variety of metrics based on past events
when deciding whether to buy or sell a security. Moving averages, bands,
and breakpoints are based on historical data and are used to forecast future
price movements.

THERE ARE THREE COMMON TECHNIQUES USED IN PREDICTIVE ANALYTICS:

Decision trees, neural networks, and regression.
1.Decision Trees
If you want to understand what leads to someone's decisions, then you may
find decision trees useful. This type of model places data into different
sections based on certain variables, such as price or market capitalization.
Just as the name implies, it looks like a tree with individual branches and
Page 202 of
150
 Page 203 of
150
leaves. Branches indicate the choices available while individual leaves
represent a particular decision.
Decision trees are the simplest models because they're easy to understand and
dissect. They're also very useful when you need to make a decision in a short
period of time.1

Page 203 of
150
 Page 204 of
150

2. Regression
This is the model that is used the most in statistical analysis. Use it when
you want to determine patterns in large sets of data and when there's a
linear relationship between the inputs. This method works by figuring out a
formula, which represents the relationship between all the inputs found in
the dataset. For example, you can use regression to figure out how price
and other key factors can shape the performance of a security.
3. Neural Networks
Neural networks were developed as a form of predictive analytics by
imitating the way the human brain works. This model can deal with complex
data relationships using artificial intelligence and pattern recognition. Use it
if you have several hurdles that you need to overcome like when you have
too much data on hand, when you don't have the formula you need to help
you find a relationship between the inputs and outputs in your dataset, or
when you need to make predictions rather than come up with explanations.

PREDICTIVE ANALYTICS VS. MACHINE LEARNING

A common misconception is that predictive analytics and machine learning
are the same things. Predictive analytics help us understand possible future
occurrences by analyzing the past. At its core, predictive analytics includes a
series of statistical techniques (including machine learning, predictive
modeling, and data mining) and uses statistics (both historical and current)
to estimate, or predict, future outcomes.
Machine learning, on the other hand, is a subfield of computer science that,
as per the 1959 definition by Arthur Samuel (an American pioneer in the
field of computer gaming and artificial intelligence) means "the
programming of a digital computer to behave in a way which, if done by
human beings or animals, would be described as involving the process of
learning."

Predictive models are used for all kinds of applications, including:

Page 204 of
150
 Page 205 of
 Weather forecasts 150

 Creating video games

 Translating voice to text for mobile phone messaging

Page 205 of
150
 Page 206 of
150
 Customer service
 Investment portfolio development

PREDICTIVE ANALYTICS - MAKES PREDICTIONS FOR THE FUTURE PROGRESS

Predictive analytics is a form of technology that makes predictions about
certain unknowns in the future. It draws on a series of techniques to make
these determinations, including artificial intelligence (AI), data mining,
machine learning, modeling, and statistics.3 For instance, data mining
involves the analysis of large sets of data to detect patterns from it. Text
analysis does the same, except for large blocks of text.
 Predictive analytics uses statistics and modeling techniques to
determine future performance.
 Industries and disciplines, such as insurance and marketing, use
predictive techniques to make important decisions.
 Predictive models help make weather forecasts, develop video
games, translate voice-to-text messages, customer service decisions,
and develop investment portfolios.
 People often confuse predictive analytics with machine learning even
though the two are different disciplines.
 Types of predictive models include decision trees, regression,
and neural networks.
==================================================================
==============================================================

Page 206 of
150
 Page 207 of
150
UNIT V
PRESCRITIVE ANALYTICS
(Introduction to Prescriptive analytics - Prescriptive Modeling - Non Linear
Optimisation
- Demonstrating Business Performance Improvement).

INTRODUCTION TO PRESCRIPTIVE ANALYTICS

THREE TYPES OF ANALYTICS

There are three types of analytics that businesses use to drive their
decision making; descriptive analytics, which tell us what has already
happened; predictive analytics, which show us what could happen, and
finally, prescriptive analytics, which inform us what should happen in the
future.

What Is Prescriptive Analytics?

Prescriptive analytics is a type of data analytics—the use of technology to
help businesses make better decisions through the analysis of raw data.
Specifically, prescriptive analytics factors information about possible
situations or scenarios, available resources, past performance, and current
performance, and suggests a course of action or strategy. It can be used to
make decisions on any time horizon, from immediate to long term.

Prescriptive analytics is the third and final phase of business analytics, which
also includes descriptive and predictive analytics.
Prescriptive Analytics entails the application of mathematical and
computational sciences and suggests decision options to take advantage of
the results of descriptive and predictive analytics.

WHAT IS PRESCRIPTIVE ANALYTICS?

Prescriptive analytics is a process that analyzes data and provides instant
recommendations on how to optimize business practices to suit multiple

Page 207 of
150
 Page 208 of
150 we
predicted outcomes. In essence, prescriptive analytics takes the “what
know”

Page 208 of
150
 Page 209 of
150
(data), comprehensively understands that data to predict what could
happen, and suggests the best steps forward based on informed
simulations.
Prescriptive analytics is the third and final tier in modern, computerized data
processing. These three tiers include:
 Descriptive analytics: Descriptive analytics acts as an initial catalyst
to clear and concise data analysis. It is the “what we know” (current
user data, real-time data, previous engagement data, and big data).
 Predictive analytics: Predictive analytics applies mathematical
models to the current data to inform (predict) future behavior. It is
the “what could happen."
 Prescriptive analytics: Prescriptive analytics utilizes similar modeling
structures to predict outcomes and then utilizes a combination of
machine learning, business rules, artificial intelligence, and algorithms
to simulate various approaches to these numerous outcomes. It then
suggests the best possible actions to optimize business practices. It is
the “what should happen.”

Prescriptive analytics is the natural progression from descriptive and

predictive analytics procedures. It goes a step further to remove the
guesswork out of data analytics. It also saves data scientists and marketers
time in trying to understand what their data means and what dots can be
connected to deliver a highly personalized and propitious user experience to
their audiences.

PRESCRIPTIVE ANALYTICS TELLS YOU WHAT SHOULD BE DONE

What is prescriptive analytics?
If descriptive analytics tells you what has happened and predictive analytics
tells you what could happen, then prescriptive analytics tells you what
should be done. This methodology is the third, final and most advanced
stage in the business analysis process and the one that calls businesses to
action, helping executives, managers and operational employees make the
Page 209 of
150
 Page 210 of
best possible decisions based on the data available to them. 150

Page 210 of
150
 Page 211 of
150
How Prescriptive Analytics Works
Prescriptive analytics relies on artificial intelligence techniques, such as
machine learning—the ability of a computer program, without additional
human input, to understand and advance from the data it acquires, adapting
all the while. Machine learning makes it possible to process a tremendous
amount of data available today. As new or additional data becomes
available, computer programs adjust automatically to make use of it, in a
process that is much faster and more comprehensive than human
capabilities could manage.
Prescriptive analytics works with another type of data analytics, predictive
analytics, which involves the use of statistics and modeling to determine
future performance, based on current and historical data. However, it goes
further: Using the predictive analytics' estimation of what is likely to
happen, it recommends what future course to take.
Numerous types of data-intensive businesses and government
agencies can benefit from using prescriptive analytics, including those in
the financial services and health care sectors, where the cost of human
error is high.
 Prescriptive analytics makes use of machine learning to help
businesses decide a course of action based on a computer program’s
predictions.
 Prescriptive analytics works with descriptive analytics and
predictive analytics, which uses data to determine near-term
outcomes.
 When used effectively, prescriptive analytics can help organizations
make decisions based on facts and probability-weighted projections,
rather than jump to under-informed conclusions based on instinct.

BENEFITS OF PRESCRIPTIVE ANALYTICS

If you’re a senior executive, looking to further optimize the efficiency and
success of your organization’s operations is always top of mind. Prescriptive
analytics is the smartest and most efficient tool available to scaffold any
Page 211 of
150
 Page 212 of
organization’s business intelligence. Prescriptive analytics affords150
organizations the ability to:
 1.Effortlessly map the path to success. Prescriptive analytic models are
designed to pull together data and operations to produce the
roadmap that tells you what to do and how to do it right the first time.
Artificial intelligence takes the

Page 212 of
150
 Page 213 of
150
reins of business intelligence to apply simulated actions to a scenario
to produce the steps necessary to avoid failure or achieve success.
 2.Inform real-time and long-term business operations. Decision makers
can view both real-time and forecasted data simultaneously to make
decisions that support sustained growth and success. This
streamlines decision making by offering specific recommendations.
 3.Spend less time thinking and more time doing. The instant turnaround
of data analysis and outcome prediction lets your team spend less
time finding problems and more time designing the perfect solutions.
Artificial intelligence can curate and process data better than your
team of data engineers and in a fraction of the time.
 4.Reduce human error or bias. Through more advanced
algorithms and machine learning processes, predictive analytics
provides an even more comprehensive and accurate form of
data aggregation and analysis than descriptive analytics,
predictive analytics, or even individuals.

Examples of prescriptive analytics

According to Inside Info, a commonly used prescriptive analytics tool is GPS
technology, since it provides recommended routes to get the user to their
desired destination based on such things as journey time and road closures.
In this instance, prescriptive analysis ‘optimises an objective that measures
the distances from your starting point to your destination and prescribes
the optimal route that has the shortest distance.’
Other areas of prescriptive analysis application, according to
data analytics firm Sisense, include the following:
 Oil and manufacturing – tracking fluctuating prices
 Manufacturing – improving equipment management,
maintenance, price modelling, production and storage
 Healthcare – improving patient care and healthcare administration by
evaluating things such as rates of readmission and the cost-
effectiveness of procedures
Page 213 of
150
 Page 214 of
 Insurance – assessing risk in regard to pricing and premium 150
information for clients

Page 214 of
150
 Page 215 of
150
 Pharmaceutical research – identifying the best testing and patient
groups for clinical trials.
==============================================================
(5.2) PRESCRIPTIVE MODELING - PRESCRIPTIVE PROCESS MODELS

Prescriptive analytics model businesses while taking into account all inputs,
processes and outputs. Models are calibrated and validated to ensure they
accurately reflect business processes. Prescriptive analytics recommend the
best way forward with actionable information to maximize overall returns
and profitability.

PRESCRIPTIVE PROCESS MODELS

There are three types of prescriptive process models. They are:
1. The Waterfall Model
2. Incremental Process model
3. RAD model
1. The Waterfall Model
 The waterfall model is also called as 'Linear sequential model' or
'Classic life cycle model'.
 In this model, each phase is fully completed before the beginning
of the next phase.
 This model is used for the small projects.
 In this model, feedback is taken after each phase to ensure that the
project is on the right path.
 Testing part starts only after the development is complete.

Page 215 of
150
 Page 216 of
150

An alternative design for 'linear sequential model' is as follows:

Advantages of waterfall model

 The waterfall model is simple and easy to understand, implement, and use.
 All the requirements are known at the beginning of the project, hence
it is easy to manage.
 It avoids overlapping of phases because each phase is completed at once.
 This model works for small projects because the requirements are
understood very well.
 This model is preferred for those projects where the quality is more
important as compared to the cost of the project.
Disadvantages of the waterfall model
 This model is not good for complex and object oriented projects.
 It is a poor model for long projects.
Page 216 of
150
 Page 217 of
150
 The problems with this model are uncovered, until the software testing.
 The amount of risk is high.
2. Incremental Process model
 The incremental model combines the elements of waterfall model
and they are applied in an iterative fashion.
 The first increment in this model is generally a core product.
 Each increment builds the product and submits it to the
customer for any suggested modifications.
 The next increment implements on the customer's
suggestions and add additional requirements in the previous
increment.
 This process is repeated until the product is finished.
For example, the word-processing software is developed using the
incremental model.

Advantages of incremental model

 This model is flexible because the cost of development is low and
initial product delivery is faster.
 It is easier to test and debug during the smaller iteration.
 The working software generates quickly and early during the software life
cycle.
 The customers can respond to its functionalities after every increment.
Disadvantages of the incremental model
 The cost of the final product may cross the cost estimated initially.
Page 217 of
150
 Page 218 of
 This model requires a very clear and complete planning. 150

Page 218 of
150
 Page 219 of
150
 The planning of design is required before the whole system is broken
into small increments.
 The demands of customer for the additional functionalities after every
increment causes problem during the system architecture.
3. RAD model
 RAD is a Rapid Application Development model.
 Using the RAD model, software product is developed in a short period of
time.
 The initial activity starts with the communication between
customer and developer.
 Planning depends upon the initial requirements and then the
requirements are divided into groups.
 Planning is more important to work together on different modules.
The RAD model consist of following phases:

1. Business Modeling
 Business modeling consist of the flow of information between various
functions in the project.
 For example what type of information is produced by every function
and which are the functions to handle that information.
 A complete business analysis should be performed to get the
essential business information.
2. Data modeling
 The information in the business modeling phase is refined into the set
of objects and it is essential for the business.
 The attributes of each object are identified and define the
relationship between objects.
3. Process modeling
 The data objects defined in the data modeling phase are changed
to fulfil the information flow to implement the business model.
 The process description is created for adding, modifying, deleting or
retrieving a data object.

Page 219 of
150
 Page 220 of
4. Application generation 150

Page 220 of
150
 Page 221 of
150
 In the application generation phase, the actual system is built.
 To construct the software the automated tools are used.
5. Testing and turnover
 The prototypes are independently tested after each iteration so that
the overall testing time is reduced.
 The data flow and the interfaces between all the components are are
fully tested. Hence, most of the programming components are already
tested.

==============================================================

(5.3) PRESCRIPTIVE MODELING - (NON LINEAR OPTIMISATION)

WHAT IS LINEAR VS NONLINEAR?

Linear means something related to a line. All the linear equations are used
to construct a line. A non-linear equation is such which does not form a
straight line. It looks like a curve in a graph and has a variable slope value.

What is the importance of nonlinear programming?

Page 221 of
150
 Page 222 of
The importance of Nonlinear Programming Applications is growing150
due to
rapidly increasing sophistication of managers and operation researchers in
implementing

Page 222 of
150
 Page 223 of
150
decision oriented mathematical models, as well as to the growing
availability of computer routines capable of solving large-scale
nonlinear problems.

What is a non linear optimization problem?

A smooth nonlinear programming (NLP) or nonlinear optimization problem
is one in which the objective or at least one of the constraints is a smooth
nonlinear function of the decision variables. An example of a smooth
1 2

nonlinear function is: 2 X 2

+X 3
+ log X3.

How do you do linear calculations?

The standard form of a linear equation in two variables is of the form Ax +
By = C. Here, x and y are variables, A and B are coefficients and C is a
constant.

What is the main characteristic of a non-linear optimization problem?

A nonlinear program (NLP) is the most general formulation for an
optimization. The objective and the constraints can be arbitrary functions of the
decision variables, continuous or discontinuous.

What is the difference between linear and nonlinear optimization?

Linear programming is a method to achieve the best outcome in a
mathematical model whose requirements are represented by linear
relationships whereas nonlinear programming is a process of solving an
optimization problem where the constraints or the objective functions are
nonlinear.

Page 223 of
150
 Page 224 of
150

Where is non linear optimization used?

At that time, applications of nonlinear optimization included problems in
chemical engineering, portfolio optimization, and a host of decision
problems in management and industrial operations.

How do you solve nonlinear programming problems?

The least complex method for solving nonlinear programming problems is
referred to as substitution. This method is restricted to models that contain
only equality constraints, and typically only one of these. The method
involves solving the constraint equation for one variable in terms of another.

What is a linear optimization problem?

A linear optimization problem can be defined as solving an optimization
problem in which the objective function(s) and all associated constraint
conditions are linear.

Page 224 of
150
 Page 225 of
150
What are the three common elements of an optimization problem?
Optimization problems are classified according to the mathematical
characteristics of the objective function, the constraints, and the
controllable decision variables.
Optimization problems are made up of three basic ingredients: An objective
function that we want to minimize or maximize.

What is a non linear programming problem?

In mathematics, nonlinear programming (NLP) is the process of solving an

optimization problem where some of the constraints or the objective function are
nonlinear.

OPTIMIZATION
The concept of optimization is now well rooted as a principle underlying
the analysis of many complex decision or allocation problems. It offers a
certain degree of philosophical elegance that is hard to dispute, and it
often offers an indispensable degree
of operational simplicity. Using this optimization philosophy, one
approaches a complex decision problem, involving the selection of
values for a number of interrelated
variables, by focusing attention on a single objective designed to quantify
performance and measure the quality of the decision. This one objective is
maximized (or minimized, depending on the formulation) subject to the
constraints that
may limit the selection of decision variable values.
Page 225 of
150
 Page 226 of
150

Different Prescriptive Analytics Approaches

It's natural to try to find the best approach to solving any problem, and
prescriptive analytics software is divided into two broad categories. On the
one hand, there are those offering modeling solutions based on business
rules, and on the other, those that use linear programming techniques.

Business Rules (Heuristics)

Rules-based modeling, known as heuristics, is good for finding solutions
quickly to complex problems. Heuristics are based on a set of predefined
rules approached sequentially. Solutions may involve the use of decision
trees, statistics and algorithms to determine answers. Heuristics are good for
narrowly-defined problems, especially those associated with operational
decisions.
Benefits of heuristics
The logical approach means heuristics work well where there are limited
options, such as in production planning or with inventory management.
Heuristics are relatively easy to understand and configure and are often
used in decision automation software providing immediate solutions.

Disadvantage of heuristics
While logical, heuristics can't provide answers which haven't been
predetermined. This means that heuristics cannot analyze all possible
scenarios, a particular limitation
of Excel-based scenario analysis. It's possible answers may not be optimal,
nor always feasible. Rules need constant maintenance to reflect changes,
and it's difficult to account for constraints.

LINEAR PROGRAMMING (OPTIMIZATION MODELING)

The goal of prescriptive analytics linear programming is to optimize a
solution. Typically, the first step is to define a model that represents
business reality, including all limitations and constraints. A key step in the
Page 226 of
150
 Page 227 of
process is model validation to ensure it reflects business realities.150
Using
complex linear programming and algorithms, the model solves for one or
more objective function, finding the best possible solution.

Page 227 of
150
 Page 228 of
150
Optimization modeling can handle numerous constraints and trade-offs to
determine the best combination of feasible business activities to optimize the
objective function.

Benefits of optimization modeling

Optimization modeling is a proven technique. Early examples of successful
optimization modeling go back over a century. It provides an optimal answer
in terms of any specified objective function. It works well in complex
business situations where there are no clear solutions. There are numerous
established software vendors.

Disadvantages of optimization modeling

Optimization modeling is slower than heuristics. Model preparation is
tedious, particularly with 3rd and 4th generation programming languages
that require advanced programming skills. Complex scenarios may take
several hours to run, although this is less of a problem with 5th generation
software packages. It may be difficult to understand how the optimization
works and users may be dependent on specialists for changes. However,
with 5th-generation optimization technology, there is no requirement for
code or programming knowledge. Thus, companies can get the speed,
agility, and flexibility that a rules-based system offers, without sacrificing
performance.

Prescriptive Analytics Software

As demand for prescriptive analytics has grown, vendors have developed
two different technologies, namely prescriptive analytics packages and
prescriptive analytics platforms.

Prescriptive Analytics Packages

These are standalone packages targeted at specific, well-defined
applications. Examples include airline ticketing, car hire, sales, marketing
and S&OP. Packages may be rules- or optimization-based. In most instances,
Page 228 of
150
 Page 229 of
150
all that's required to get up and running is configuration such as setting up
user accounts, security and connection to data sources. Minimal
customization is required.

Page 229 of
150
 Page 230 of
150

Advantages of packages
Especially with cloud-based packages, configuration is fast and setup can
be accomplished within a few days. Packages work well with standardized
applications, especially in large organizations with many branches.
Solutions require minimal IT involvement.

Drawbacks of packaged solutions

Solutions may not perfectly match applications, possibly requiring
organizations to change their work practices to match how the software
works. There aren't many applications for small industries, nor for complex
problems. Users are reliant on vendors for updates and software fixes.

Optimization Platforms
These comprise of two parts, the modeling platform and an optimization
solver. They're sometimes sold as separate solutions, although in other
instances, vendors supply a complete platform comprising both functions. In
both instances, the user must research, design and develop the model.
Third and fourth generation optimization modeling platforms are based on
high-level programming languages such as Python, Ruby and SQL, and
they require a degree of expertise to write algorithms that define the
model and also to validate the model. Fifth generation modeling software
that uses a drag-and-drop approach to create a constraint-based model is
simpler and easy to use.

Advantages of optimization platforms

Optimization platforms can solve almost any analytical problem. An
optimization platform allows users to create highly complex models that
accurately represent the business, industry or problem to be solved. They
work well for specialized applications and complex problems. The
technology is mature and there's good vendor support.
Drag-and-drop 5th generation programming languages are easy to use, are
Page 230 of
150
 Page 231 of
interpretable by non-data scientists, and don't require advanced 150
programming skills to

Page 231 of
150
 Page 232 of
150
prepare. They're able to have a greater impact on value without sacrificing the
need for flexibility, agility, and user-friendly interfaces.

Disadvantages of optimization platforms

Apart from 5th generation languages, an OR expert is needed to write the
complex math and algorithms to define the model and solver. In most
instances, it's also necessary to develop end-user interfaces, and each
solution is bespoke.

Problems That Can Be Solved by Prescriptive Analytics

Prescriptive analytics differs from other forms of analytics in that it's able to
determine the right decisions to take to maximize an organization's key
objectives. Whether it's to improve profit, or for operational planning or to
optimize a function, prescriptive analytics provides specific, measurable
answers to these questions. Prescriptive analytics is the right tool for any
complex situation where there are so many variables and possible outcomes
that it is otherwise impossible to determine the right course of action.
There are many examples of prescriptive analytics being used to improve
operations and profitability. Here at River Logic, we work with all ranges of
industries and company sizes to deploy prescriptive analytics solutions, like
Food and Beverage or Wood Products manufacturers.
One typical case demonstrates how a pulp and paper manufacturer running
four paper mills used prescriptive analytics to increase production volume
by 65 thousand tons while increasing operating income. Another involved a
manufacturer of wood products for residential and construction markets
with 14 manufacturing facilities that needed to optimize manufacturing
performance in the face of increased regulation. Using prescriptive
analytics, Cox Industries was able to increase forecast accuracy, identify
ways to reduce internal costs and increase profitability.
Prescriptive analytics is a value tool for any business seeking to improve
operational performance. While model development requires commitment
and a degree of investment, the results show that, in most instances, the
Page 232 of
150
 Page 233 of
150these
financial benefits significantly exceed implementation costs. It's for
reasons that Gartner and others forecast widespread growth of
prescriptive analytics over the next few years.
==============================================================

Page 233 of
150
 Page 234 of
150

(5.5) PRESCRITIVE ANALYTICS - BUSINESS PERFORMANCE IMPROVEMENT -

DEMONSTRATING BUSINESS PERFORMANCE IMPROVEMENT

What is Prescriptive Analytics?

It is an area of business analytics (BA) that is devoted to determining the
best course of action to be taken, given a specific set of circumstances or
opportunities. Prescriptive analytics can also provide options for how to
maximize a future opportunity or minimize a future threat, as well as explain
the implications of each alternative.

Prescriptive Analytics Definition

Prescriptive analytics is the branch of analytics that seeks to provide “what
should be done, or what can be done” in light of data. The basic concept of
prescriptive analytics is to consider the business impact on various aspects.
Prescriptive analytics involves the use of advanced mathematical models
and algorithms, using artificial intelligence, to provide an automated solution
to a problem.

Role of Prescriptive Analytics in Business Decision Making

One of the most important capabilities to develop in any large business is
being able to take a systematic approach to analytics. Making the right
decisions is a challenge for businessmen, more so if there is limited data to
support the decision-making process. What’s more, past experiences aren’t
always reliable indicators of future outcomes, so decisions based only on
historical data may sometimes be incorrect. Getting started with
prescriptive analytics.
Prescriptive analytics provides specific options that can be implemented,
which are then compared to criteria to determine which are the most
appropriate to be adopted. It can generate recommendations or insights that
will help business leaders make better, faster decisions to optimize the
Page 234 of
150
 Page 235 of
value of their data. 150

For example, if a business wants to improve its service, prescriptive

analytics can assist in determining what changes can be made to the
customer experience (including price and product selection).

Page 235 of
150
 Page 236 of
150

HOW DOES PRESCRIPTIVE ANALYTICS WORK IN THE OVERALL

BUSINESS DECISION PROCESS?
First, the company should understand what is happening in its business
based on current trends and historic data. Based on these inputs,
prescriptive analytics can be used to change the business for the better.
According to us, any company that is using predictive analytics should also
be using prescriptive analytics to identify opportunities, address risks and
improve business performance. Using analytical models and algorithms to
make decisions and recommendations, businesses can use prescriptive
analytics to go a step beyond just trying to understand what is likely to
happen in the future. Prescriptive analytics examines information to
understand the impact on the business and prescribe the appropriate
action or next best step for improvement.

TYPES OF PRESCRIPTIVE ANALYTICS

When it comes to prescriptive analytics, the three main subtypes are:
1. Operational Prescriptive Analytics – typically used in business settings.
This type of prescriptive analytics is the most common because it is most
suited to business- driven decision-making.
2. Financial Prescriptive Analytics – often used in conjunction with
Operational Prescriptive Analytics.
3. Prospective/Strategic Prescriptive Analytics – this prescriptive analytics
type is most often used in an environment where business plans are made
and implemented with the full understanding of short-term goals.

Prescriptive analytics, output is not a prediction of what might happen, but

rather what should happen to achieve desired outcomes.
Scenario – The first step in prescriptive analytics is to identify the objective.
Scenarios should be clear and concrete; they should show exactly what will
happen as a result of a change in your data. Two or three scenarios (such
as the following) are normally sufficient. Scenarios should cover all relevant
Page 236 of
150
 Page 237 of
aspects of the project, both positive and negative. 150

Page 237 of
150
 Page 238 of
150
Inputs – What does the output look like? What data should be collected?
What methods will be used for the coalition of the data?
Business objective – What is the business objective? What is the expected
value of the product/service/whatever? What are the most important
constraints?
Outputs – What is the expected outcome? How will it be measured?
We do this so we know what outcome we are eventually trying to achieve.
Prescriptive analytics is typically used in situations where there is no causal
relationship between two or more variables. It is useful when you want to
know how to
change the condition of the dependent variable in order to maximize the
likelihood of the outcome you are trying to achieve.

TOOLS REQUIRED FOR PRESCRIPTIVE ANALYTICS

Prescriptive analytics tools range from high-level programming languages to
integrated ERP tools to solution-specific software packages. These include
SAS, Excel, SQL, Visual Basic, Visual C++, Visual Basic for Applications
(VBA), etc.
Most of these tools have a prescriptive analytics capability built into them,
although some may require custom programming.
Pre-built data analysis toolkits: The most commonly used of these is SAS. The
toolkit includes operations and analytical tools such as scatter plots, ratio
analysis, and linear regression that can be used for prescriptive analytics.
Tools that can be programmed into specific enterprise applications such as
SAP and Oracle also include prescriptive analytics capabilities.
Custom tools: These are primarily developed to the specific needs of the
user. Many of these tools are freeware or have shareware versions that are
free to use without the need for a license.
Examples of these prescriptive analytics tools include network flows,
graphical user interfaces for data processing, and visualization tools
such as Excel.
Operating systems: In addition to the various prescriptive analytics platforms,
Page 238 of
150
 Page 239 of
150
different operating systems have been designed with features specifically
designed to aid in prescriptive analytics. For example, Microsoft’s SQL
Server, Red Hat’s Enterprise Linux, and IBM’s AIX are three systems
designed to facilitate the implementation of

Page 239 of
150
 Page 240 of
150
prescriptive analytics by offering faster processing speeds with more robust
memory capabilities.

Decision-making is an important capability of any organization.

Prescriptive Analytics is a branch of business analytics that deals with
determining the best course of action to take, based on a set of
circumstances or opportunities.
Prescriptive analytics is already being applied in industries such as
healthcare, insurance, and finance.

WHAT IS THE DIFFERENCE BETWEEN PREDICTIVE AND PRESCRIPTIVE

ANALYTICS
The key difference between prescriptive analytics and traditional predictive
analytics is that the former tells you how to implement changes.
Due to the nature of predictive analytics, it indicates what may unfold but
does not provide guidance as to how to proceed so that a business can be in
the driver’s seat to control these “future” events. Traditional predictive
analytics involves the use of data- driven models and algorithms to build a
model that provides forecasting or inferences about what will happen in the
future based on existing data. However, the output of the model is not data-
driven, instead, it is a series of predictions or inferences about what will
happen in the future.
Prescriptive analytics, on the other hand, helps determine the most
profitable decision. The decision-making process can be accomplished
through the use of natural language processing, clustering, clustering,
classification, decision trees, neural networks, fuzzy logic, Bayesian
networks, rule-based analytics, and so on.
While the problem may be predicting the future, this is not the primary
objective of prescriptive analytics; that is best left to predictive analytics,
especially in industries that require high accuracy. For example, if you are
operating a nuclear power plant or manufacturing airplane parts, then
predictive analytics can help reduce the risk of accidents. Predictive
Page 240 of
150
 Page 241 of
150
analytics relies on historical data to predict future events. This method is
used to forecast customer behavior, product demand, and financial
performance.

Page 241 of
150
 Page 242 of
150
Prescriptive analytics is largely dedicated to the question “how to?” rather than
“what if”.
While one could think of predictive analytics as determining the outcome of
a forecast, it’s still about achieving an outcome. Prescriptive analytics, on
the other hand, don’t really care what the outcome is: all it is concerned
about is what should happen and how to achieve it. While predictive
analytics and prescriptive analytics might seem like two sides of the same
coin, they’re really not. Predictive analytics is about providing support for
an existing decision, while prescriptive analytics helps you develop a new
decision — there’s still a lot of overlap between the two, but we’ll get to
that.
One example to differentiate between predictive and prescriptive is:
You need a predictive model to find out what customers are likely
to buy. But you need
prescriptive models to find out which is the best communication channel, or
how many emails you should send to increase the chance of purchase.

HOW PRESCRIPTIVE ANALYTICS BENEFITS BUSINESS

PERFORMANCE IMPROVEMENT
The major disciplines of prescriptive analysis are operations research,
machine learning (ML), natural language processing (NLP), and applied
statistics, with many other sub- disciplines. They help in:
1. Building repeatable and scalable processes: To accurately predict
outcomes, one has to create an in-house simulated environment.
Keeping up with the fluid nature of the market, prescriptive analytics
builds off historical data and allows businesses to run what-if analysis
quickly. Once the business has run multiple scenarios, it can adopt the
most efficient option and quickly make it repeatable and scalable.
2. Optimising business actions with monthly plans to meet ROI: Be it
pricing, marketing, or sales, business owners can predict the course
of action that can deliver optimal ROI.
3. Removing underperforming channels: In a large business,
Page 242 of
150
 Page 243 of
underperforming sources of revenue often go unnoticed for 150
too long.
Prescriptive analytics lets you identify such channels quickly and take
necessary actions. You can divert the budget to those products that
deliver maximum returns.

Page 243 of
150
 Page 244 of
150
4. Achieving higher agility: By simulating and running different
scenarios of sudden market shifts, you find the best ways to respond
to those shifts quickly and to your advantage. You get to make near-
time decisions instead of waiting for weeks.
5. Creating long-term strategies: Prescriptive analytics removes data
silos and brings teams together in a collaborative model for the long
run.
6. Managing risk management: By answering complex questions related
to demand and supply, your business can optimise investments and
reduce risk.
7. Fighting retail fraud: Prescriptive analytics is taking the guesswork out
of fraud management. Especially after the pandemic, retailers are
identifying fraud impact and using data and tools to detect fraudulent
e-commerce returns claims and minimise cashier fraud in stores.
Knowing the right solution to the problem is half the battle won. At Infosys
BPM, we’ve got more than just the know-how. For organizations on the
digital transformation journey, agility is key in responding to a rapidly
changing technology and business landscape.

PRESCRIPTIVE ANALYTICS: MANAGE MANUFACTURING COSTS

AND IMPROVE ROI
Today’s manufacturing organizations operate in a dynamic
environment characterized by increased complexity and uncertainty. The
financial performance of manufacturers hinges on their ability to manage
production costs efficiently, while rapidly adapting to constantly changing
conditions, from demand fuctuations to delivery challenges.
Prescriptive analytics helps companies see where process
improvements could have the biggest, most immediate impact on their
bottom lines.
Predictive analytics helps companies understand the drivers behind
customer buying patterns to anticipate which products customers want,
how many they want and when. Prescriptive analytics, on the other hand,
Page 244 of
150
 Page 245 of
150
optimizes production planning, scheduling, inventory and supply chain
logistics to meet business requirements.
Through a combination of mathematical algorithms, machine learning and
artificial

Page 245 of
150
 Page 246 of
150
intelligence, a prescriptive analytics solution can recommend the optimal
action plan likely to drive specific business outcomes.

Prescriptive analytics techniques such as decision optimization can

tackle highly complex problems ranging from hundreds to millions of
constraints and variables that could never be analyzed manually. Decision
optimization technology also makes it easier for non-technical users to
factor in constraints, tradeoffs and multiple objectives, for faster, better
answers to questions like:
 How should we balance service levels with production constraints?
 What maintenance should we do to avoid a predicted failure in a machine?
 When should we reduce SKUs or introduce new products?
 Which activities should be assigned to which workers and when?
 How much overtime will be necessary in a specific period?

Maximizing decision value

The real payoff of decision optimization is the ability to make reliable
business decisions that create value. Optimization techniques can drive
huge efficiencies in dynamic manufacturing environments, helping
manufacturers make decisions that improve performance and profits.
Production planning
To maximize profit, manufacturers must be able to respond to market
demand with optimal production cost, speed and flexibility. The problem is
determining how much of each product to produce, when to produce it and
in which location. Demand can fluctuate significantly due to seasonal
trends and other factors. Factories have limited production resources, so
the challenge lies in considering all constraints to maximize use of available
equipment and personnel, minimize product costs and downtime, and
deliver orders on time.
Many leading manufacturers rely on decision optimization solutions to find
the best possible ways to make use of their facilities, employees and raw
materials for increased profits. To boost manufacturing efficiency,
Page 246 of
150
 Page 247 of
150
Continental Tires uses a cutting-edge solution based on IBM Decision
Optimization to optimize production across 20 plants.

Page 247 of
150
 Page 248 of
150
The solution eliminates bottlenecks and enables the best possible use of
materials, staff and machine capacity.
Supply chain management
Manufacturers have a finite number of trucks, warehouses and drivers and
a perhaps infinite number of potential delivery addresses. On any given
day, they need to decide how many drivers and trucks to put on the road,
but also need to keep the costs of equipment, fuel and drivers to a
minimum while meeting delivery commitments.
FleetPride, North America’s largest distributor of truck and trailer
parts in the independent heavy-duty aftermarket channel, is transforming
its supply chain management with IBM Decision Optimization. The solution
helps FleetPride work out optimal warehouse locations, minimize delivery
time and costs across its network. That results in reduced labor costs and
higher revenues.
Detailed scheduling
With products becoming more complex and supply chains more extended,
production scheduling is often highly complex. Production facilities may only
have a few days each month to handle specific customer orders.
Optimization considers not only asset use and production objectives in
scheduling decisions, but also their impact on shift configurations, selection
of regular versus overtime labor and other constraints.
Inventory optimization
Stocking the right products in the right quantities at the right locations
requires precision. Decision optimization software helps firms manage their
inventories to meet customer demand while reducing costs. It enables
firms to compare multiple planning scenarios using what-if analysis and
choose the best option, avoiding under- and overstocks and freeing up
capital for reinvestment elsewhere.
Maintenance scheduling
In manufacturing, when an asset breaks down, every minute lost is costly.
When equipment breaks down, it reduces profitability in a variety of ways,
including production downtime, higher labor costs per unit, and added stress
Page 248 of
150
 Page 249 of
on employees and machines. 150

Decision optimization can recommend the best time and sequence for
scheduling maintenance tasks in relation to production targets, downtime,
inventory requirements and other interdependencies. The results can then
be fed into companies’ enterprise resource planning, business intelligence,
logistics and other enterprise systems to

Page 249 of
150
 Page 250 of
150
continuously reoptimize decisions as conditions change. This adds up to
major time savings, increased agility and greater ROI.
Start turning predictions into decisions
Manufacturers ready to take the next step toward prescriptive
analytics should focus on complex decisions where they have a lot of data.
These should be in areas where they are already getting good results from
descriptive and predictive analytics but need help turning those predictions
into decisions.
When it comes to solving complex manufacturing challenges, decision
optimization can help companies stay focused on their goals. IBM Decision
Optimization offers all the capabilities manufacturing firms need to
capitalize on the power of prescriptive decision making.

WHAT IS PRESCRIPTIVE ANALYTICS, AND

WHAT CAN IT DO FOR YOUR BUSINESS?
A great tool that supports businesses, optimizing resources, and increasing
operational efficiency.
Prescriptive Analytics is one of the steps of business analytics, including
descriptive and predictive analysis. It suggests decision options to take
advantage of the results of descriptive and predictive analytics.
It can be utilized to find a solution among various variants, using different
simulation and optimization techniques to indicate the path that should be taken.
With Prescriptive Analytics, companies can get smart recommendations to
optimize the next steps in their strategy.
Along with predictive analytics, prescriptive analytics help to create a
more effective data-based strategy.
Both predictive and prescriptive analytics is critical to making business
decisions based on data.
However, the most significant difference between predictive and prescriptive
analytics is that predictive analytics predicts what will happen in the future.
In contrast, prescriptive analytics offers specific recommendations for
changing the future.
Page 250 of
150
 Page 251 of
150
With Prescriptive analytics, we can find a solution among various variants
to optimize resources and increase operational efficiency. This tool uses
different simulation and optimization techniques to indicate the path that
should be taken.
A prescriptive analysis is based on:
 Operations investigation
 Predictive Analysis
 Mathematical techniques and statistics
Its application seeks to determine each assumption’s limitations based on
the study of data and applying mathematical algorithms and probabilistic
techniques.
It can be said that it is a learning process that adapts to obtain the best
possible result in all real situations that must be faced.

WHY PRESCRIPTIVE ANALYSIS MATTERS TO YOUR BUSINESS?

Thanks to information obtained through prescriptive analysis, it is
possible for companies to make future decisions, such as:
 Calculate past sales of a product to determine the number of replacements.
 Know the tendency of customers in certain products to launch
marketing campaigns, according to users’ needs.
 Predict equipment failures, which provides for maintenance at the right
time.
 Know customers’ purchasing habits and punctuality of payment to
determine whether it is appropriate to grant credit.
It is possible that some of these decisions can be made manually and
correctly. However, the information is bigger and more complicated, and the
processes, although more complex, need to be resolved urgently.

PRESCRIPTIVE ANALYSIS HAS BENEFITS SUCH AS:

 Optimization of processes, campaigns, and strategies.
 Minimizes maintenance needs and interconnects them for better conditions.
 Reduce costs without affecting performance.

Page 251 of
150
 Page 252 of
 It increases the likelihood that companies will approach and150
plan
for internal growth properly.
 Qualitative research method — know the characteristics that distinguish it.

Page 252 of
150
 Page 253 of
150
 Production optimization.
 Efficient supply chain management.
 Improved customer service and experience.
Due to its complexity, there are still few companies that use prescriptive
analysis. However, prescriptive analysis benefits have already become
evident in many fields, including, but not limited to, healthcare, insurance,
financial risk management, and sales and marketing operations.
Among its most significant advantages, it stands out that it allows decision
making based on data, Allowing an end-to-end view of costs, processes,
and performance.
It is possible to quantify risks and have access to actions considered ideal in
different circumstances. Algorithms have the ability, through current data,
to predict consequences arising from each decision made.
Therefore, it allows you to follow the path that offers more satisfactory results.
The prescriptive analysis allows more effective planning to be carried out in
Marketing and Sales actions, bringing information that significantly impacts
business intelligence. Therefore, decisions are made according to facts,
knowing the consequences that will arise from them.
Despite the prescriptive analysis potential, it will only affect a joint
work between machine and human being.
That’s because technology doesn’t make decisions alone. She organizes the
information, analyzes the scenario, and indicates the best thing to do,
leaving the professional to proceed with the suggestions.

Conclusion
As we saw, Prescriptive Analytics has great potential to support businesses,
optimizing resources, and increasing operational efficiency.
==================================================================
==============================================================

Page 253 of
150
 Page 254 of
150

LESSON QUESTIONS - (2 MARKS for some questions) / (15 Marks for some
questions)
SL QUESTIONS
No.
1 What is business analytics?

2 What are the concepts of business analytics?

3 What are the components of data analytics?

4 What are the various Terminology in Business Analytics

5 Explain Data Processing Software

6 Explain Data Visualization with two examples.

7 Define Geospatial Analytics

8 How Pivot Table is used to summarize data

9 Explain the methods of Data Base Management

10 Definition of Descriptive Analysis

11 Definition of Predictive Analysis

12 Definition of Prescriptive Analysis

13 How Information Respository helps in Decision Making

14 Explain Statistical Analysis and its various benefits

Page 254 of
150
 Page 255 of
150

15 In Data Analytics what is the difference between Variety

Data, Velocity Data & Volume Data.

16 Explain the duties of Data Analyst

17 Describe two Business Analytical Software and its benefits.

18 What are the three main Components of Business Analytics

19 Why Non Linear Optimization Model is used in Business

Analytics.

20 Mention 5 Mathematical Models used in Business Analytics

21 How does business analytics help in decision-making?

22 Is is possible for Business analytics to help organizations

to reduce risks.

23 How Business Analytics helps in Competitive Advantage.

24 What is HR analytics?

25 What is an information management policy?

26 Explain the responsibilities of Chief Information

Governance Officer (CIGO):

27 Explain the responsibilities of ICT Statt

28 Give examples of Internal & External Data Sources in Business

Organization.

Page 255 of
150
 Page 256 of
150

29 What is SQL and its advantages in Data Sets & Data Bases.

30 What is the Difference between Reliability-data and Validity-data

31 How Data Quality is evaluated

32 Explain the importance of Master Data Management

33 What is Change Management - How Business Analytics Models

help in Change Management.

34 What are the functions of Business Analyst in Organizations.

35 WHAT IS DESCRIPTIVE ANALYTICS

36 How is data visualization used in descriptive analytics?

37 Why are visuals so important with descriptive analytics?

38 What is data visualization and exploration?

39 Explain the main difference between Inferential Statistics and

Descriptive Statistics.
40 Why is Descriptive Statistics Important?

41 What Are Descriptive Statistics? Give Examples

42 Explain the Types of Descriptive Statistics

43 What are mean and standard deviation? in Descriptive Statistics

Page 256 of
150
 Page 257 of
150
44 Can descriptive statistics be used to make inference or
prediction?

45 What is Data Visualization and its advantages in Business

Analytics

46 What are the different forms of data visualization

47 Why is Data Visualization Important?

48 What is Variable in Statistical Data

49 Difference between Quantitative Data & Qualitative Data

50 What are the types of Variables

51 Explain the Categories of Descriptive Statistics

52 Does descriptive analytics have probability distribution?

53 What is descriptive probability?

54 What is the purpose of descriptive statistics?

55 Explain Bernoulli Trials and give one formula of Binomial

Distribution

56 What is Probability Density Function in Variables

57 In Samples of Data what is Normal Distribution

58 In Samples of Data what is “bell curve“ or the “Gaussian curve“.

59 How do you analyze descriptive analytics?

Page 257 of
150
 Page 258 of
150
60 What techniques are used in descriptive analytics?

61 What is meant by predictive analytics?

62 What is the importance of predictive analytics?

63 How do you develop a predictive model?

64 Which of the following techniques is used in predictive

analytics?

65 Explain the six steps of the Predictive Analytics Process

66 What can you do with Predictive Analytics?

67 Explain the Advantages of Predictive Analytics

68 What is predictive modeling?

69 What are the types of predictive models

70 Describe the Common algorithms for predictive modelling

71 Explain the Benefits of predictive modeling

72 What are the Predictive modeling tools & Software Tools

73 What is the difference between data mining and predictive

analytics?

74 Why data mining is important in predictive analytics?

75 What is Data Mining in Business Analytics

Page 258 of
150
 Page 259 of
150
76 Explain the 6 Tasks and Factions of Data Mining 98

77 What are the Techniques used to conduct Predictive Analytics

on a Data
Set.
78 EXPLAIN THE VAARIOUS APPLICATIONS OF PREDICTIVE 104
ANALYSIS THROUGH DATA MINING.

79 ANALYSIS OF PREDICTIVE ANALYTICS 106

PREDICTIVE ANALYTICS IS A DECISION-MAKING TOOL IN
A VARIETY OF INDUSTRIES.

80 WHAT ARE THREE IMPORTANT COMMON TECHNIQUES USED

IN PREDICTIVE ANALYTICS:

81 UNIT V 110
PRESCRITIVE ANALYTICS
What Is Prescriptive Analytics?

82 Explain the Benefits of Prescriptive Analytics in Business 112

Organizations, with examples.

83 Describe the three types of prescriptive process models - State 114

the Advantages & Disadvantages of each model.

84 PRESCRIPTIVE MODELING - (NON LINEAR OPTIMISATION) 118

What is the importance of nonlinear programming?
85 What is the difference between linear and nonlinear 119
optimization?

86 Explain the concept of Optimization.

87 What are the various methodology and software techniques

Page 259 of
150
 Page 260 of
used in 150

Page 260 of
150
 Page 261 of
150
Prescriptive Analytics

88 Explain the following Software Categories in Prescriptive

Analytics -
(1) Business Rules (Heuristics) & (2) LINEAR
PROGRAMMING (OPTIMIZATION MODELING)
89 How Does Prescriptive Analytics Work In The Overall Business 126
Decision Process?

90 WHAT ARE THE SOFTWARE PACKAGE TOOLS & 127

STATISTICAL METHODS REQUIRED FOR PRESCRIPTIVE
ANALYTICS
91 WHAT IS THE DIFFERENCE BETWEEN PREDICTIVE 128
AND PRESCRIPTIVE ANALYTICS

92 HOW PRESCRIPTIVE ANALYTICS BENEFITS BUSINESS 129

PERFORMANCE IMPROVEMENT

93 What are the benefits of Prescriptive Analytics when 134

implemented in all
the Departments of a Business Organization.

Page 261 of
150