Business Analytics

UNIT - I
Chapter 1 : Introduction
Business analytics is combination of two concepts Business (which is commercial activities
of making money) and Analytics (which is systematic analysis of data using math, logic, and
science).
Business analytics involves using data to understand business operations and make
decisions. The primary goal of business analytics is to transform raw data into actionable
insights, helping businesses make better decisions, improve customer experience, optimize
processes, increase profits, and reduce risks.
It involves collecting, cleaning, and transforming data, then using statistical analysis and
data visualization tools to find patterns and trends. It also uses machine learning and
predictive models to forecast future outcomes and make accurate predictions.

Large corporations but also small and medium-sized enterprises (SMEs) can benefit from
business analytics. Advances in technology and user-friendly tools have made it accessible
for businesses of all sizes to leverage data-driven insights.
 DATA
Data refers to raw material, facts and figures such as numbers, text, images and
observations or recordings that needs to be processed or parsed to become structured
before any further work can be done on them.

Data can be divided into two main categories:

1. Qualitative (Categorical):
• Nominal: No order (e.g., gender, languages spoken)
Nominal data is a type of categorical data that represents distinct groups or categories
without any inherent order or ranking. Nominal data is often analysed using frequency
counts or percentages, allowing researchers to understand the distribution of different
categories within a dataset.
• Ordinal: Ordered (e.g., small, medium, large)
Ordinal data is a type of categorical data that has a defined order or ranking among its
categories. Ordinal data reflects a relative position or hierarchy, the categories here
indicates a sequence, allowing for comparisons between them.
2. Quantitative (Numerical):
• Discrete: Countable (e.g., number of items)
When the data values are distinct and separate, and they can take on certain values
only, they are called discrete data. Discrete data can be only counted, not measured.
• Continuous: Measurable (e.g., height)
Continuous data represent measurements and takes any value within a range, not
counts. Like: height, weight and distance.

* Scale data
Scale data is also known as continuous or interval data, it is numerical data that can be
measured on a scale with meaningful intervals. This data type allows for both comparison
and mathematical operations, such as addition and subtraction.
Examples of scale data include temperature (in degrees), weight (in kilograms), and time (in
seconds).
Scale data is characterized by having a true zero point, which signifies the absence of the
quantity being measured (e.g., zero weight means no weight). This type of data is vital for
statistical analysis, as it provides detailed insights into variations and relationships.
DATA SCIENCE
Data Science is an interdisciplinary field that combines statistics, data analysis,
and machine learning to obtain meaningful insights and knowledge from data. It is
based on the processes of gathering, analysing data, and making informed
decisions by using the patterns that have evolved.

Data Science helps in tasks such as forecasting revenues, optimizing routes,

creating promotional offers, and even predicting election outcomes.

Data Science is applied in areas like banking, healthcare, manufacturing, and e-

commerce.
Data Analytics
Data analytics refers to the whole process of examining datasets in order to find
trends, patterns, relationships, and other insights that might help in the decision-
making processes. It uses various techniques, statistical methods, algorithms,
and computational tools to process data for analyzing and interpreting it
meaningfully.

Analytics is often regarded as forward-looking phenomenon, as it aims to identify

the patterns and trends in data that can be used to answer questions, make
predictions and optimize future outcomes.

There are four main types of data analytics: descriptive, diagnostic, predictive and
prescriptive.
Data Analysis
Data analysis refers to inspecting, cleaning, transforming, and modeling data to
discover useful information, draw conclusions, and support decision-making. It is
mostly focused on extracting insights and answering specific questions from data,
whether qualitative or quantitative. In analysis each step ensures data quality and
prepares it for meaningful analysis and conclusions.

Data Analysis Process:

1. Data Collection: Data analytics begins with the data gathering from different
sources, sources like surveys, databases, or spreadsheets or data sources
from other locations. Quality of the collected data will determine the accuracy
of the analysis.
2. Data Cleaning: In this step anomalies are corrected to create complete data
set. It involves handling missing values, removing duplicates, resolving
inconsistencies, and addressing any data quality problems or standardizing
data for reliability.
3. Data Exploration: Using statistics and visual tools (EDA) to spot patterns, trends,
and anomalies. Exploratory Data Analysis (EDA) applies statistical graphics and
summary statistics to make conclusions based on patterns, correlations, and
outlying observations.

4. Data Transformation: This is the steps of transforming data into a suitable

format for analysis involve normalizing values, aggregating data, or creating new
features to enhance the effectiveness of the model.

5. Data Modeling: Here, statistical, mathematical, or machine learning models are

applied to the data for answering specific research questions. Common
techniques used include regression analysis, classification algorithms,
clustering, and time-series analysis.

6. Data Interpretation: This is the last stage of data analysis wherein results are
interpreted and conclusions drawn as well as using the insights to support
decision-making or make recommendations.
 Analytics vs Analysis
BASIS ANALYTICS ANALYSIS
Process of inspecting, cleaning,
Broader process of examining data to
Meaning and modeling data to extract
uncover trends, patterns, and insights.
useful information.
Broad – includes analysis, prediction, Narrow – focuses on answering
Scope
and decision-making. specific questions.
Subset Analytics include analysis Analysis is the subset of analytics
Data analysis + predictive modeling, Data cleaning, transformation,
Steps Involved
machine learning, etc. interpretation
Advanced tools like machine learning, Basic statistics, spreadsheets,
Tools
statistical models, R, Python, etc. charts.
Explore data from past for future Understand past to make logical
Purpose
predictions and decisions decisions
Using past sales data to forecast future
Example trends and suggest marketing Analyzing sales report to see
what happened last quarter.
strategies.
Application of Analytics
The applications of business analytics is diverse and spans across multiple functional areas
within an organisation and used to improve efficiency, decision-making, and performance.

Applications of Analytics in Finance

Consumer Insights: Understanding customer behavior and preferences.
Algorithm Trading: Using algorithms to automate trading strategies.
Fraud Detection: Identifying and preventing fraudulent activities.

Benefits:-
Reduced Human Error: Minimizes mistakes in financial transactions.-
Enhanced Decision-Making: Turns data into actionable insights.-
Clear KPI View: Helps track key performance indicators like revenue and net income.-
Vital Metrics Scrutiny: Analyzes important metrics and detects fraud in revenue turnover.

Skills for Finance Data Analysts:- Data Mining, Financial Analytics, Business Models
Understanding, Financial Forecasting, Risk Management, Advanced Analytics, Data
Management, Python, Automation, Data Science etc.
2. Applications of Analytics in Marketing

1. CRM (Customer Relationship Management)

Purpose: Understand customer tastes and preferences.
Benefit: Smoothens the customer's journey by anticipating decision-making behavior.
2. Brand Positioning
Purpose: Position the brand effectively in the market using growth statistics and customer
base data.
Benefit: Helps decide on niche marketing and understand brand popularity among certain
customer groups.
3. Optimizing Prices
Purpose: Track competitor prices and inflation rates.
Benefit: Predicts purchasing power and suggests optimal pricing strategies.
4. Designing Campaigns and Advertisements
Purpose: Predict consumer behavior and improve decision-making.
Benefit: Determines ROI of marketing efforts and provides deep insights into the target
audience
3. Applications of Analytics in Human Resources (HR)
1. Improving Talent Acquisition
Analyses recruitment channels, candidate profiles, and hiring outcomes. And helps to
identify effective sourcing strategies, optimize job postings, and select better candidates.

2. Preventing Workplace Misconduct

Identifies trends and common occurrences related to misconduct. Analyzes employee
data to proactively identify and address potential misconduct risks.

3. Staff Retention and Turnover Management

Calculates crucial metrics like staff turnover rate. Analyzes historical data to implement
strategies for increasing staff retention and engagement.

4. Measuring Key Performance Indicators (KPIs)

Measures and tracks employee performance and productivity. Helps evaluate the
effectiveness of performance management systems and align performance with goals. -
Enables estimation of Return on Investment (ROI) for each employee.
5. Identifying Skill Gaps - Utilizes data visualization and automation tools to plot a skills
grid. Highlights areas of strength and weakness to develop targeted learning programs.

6. Creating an Engaging Work Environment - Provides insights about workforce types,

cultural dynamics, and work preferences. - Designs initiatives to foster engagement and
promote a positive company culture.

7. Identifying Upskilling Opportunities - Collects data on areas where employees need

upskilling. - Offers targeted upskilling opportunities based on training data and
performance metrics
4. Applications of Analytics in Healthcare
Analytics plays a crucial role in management of patients in healthcare sector. It broadly
covers areas like

1. Diagnosis and Treatment

One of the significant application of analytics is medical imaging that is used to diagnose
the disease and prescribe an appropriate treatment. In Medical Imaging algorithms
interpret MRI and X-ray results to identify patterns, tumors, or anomalies. These algorithm
models can diagnose irregular heartbeats faster than cardiologists.
2. Drug Discovery
Enables pharmaceutical companies in discovering drugs for hard-to-detect diseases.
Example: AI company named Benevolent AI developed a smart device to create medicines
for dreadful diseases.
3. Disease Prevention
Uses genetics of the person and his past history to predict potential health issues.
Identifying early signals of diseases helps to prevent them before they becomes incurable.
4. Miscellaneous Applications
Other application of analytics like Post-Care Monitoring, Hospital Operations, Prescription
Auditing, Predicting Disease Outcomes, Tracking Prescriptions, Substance Abuse Risk etc.
Big Data
Big Data refers to extremely large and complex datasets generated rapidly from
various sources, which traditional data processing tools cannot handle efficiently.
Big data helps businesses analyze customer behavior, predict trends, and make
data-driven decisions.

Characteristics of big data or 5 V’s of big data:

1. Volume: Refers to the massive amount of data generated daily. Measured in
terabytes, petabytes, or exabytes. For example, the likes, comments and post
shared by billions of users of Facebook every day.
2. Velocity: The speed at which data is created, processed, and analyzed.
Requires real-time or near real-time processing. Like stock market systems
process millions of transactions per second to give real time updates.
3. Variety: Refers to the different forms of data, Structured (organized, easy to
analyze), Unstructured (messy, like videos, images), Semi-structured (a mix of
both). Example: YouTube videos, tweets, emails.
4. Veracity: It refers to the accuracy, quality, and trustworthiness of data. Data can
be messy, incomplete, or misleading, hence we need filtering before processing.

5. Value: The insights and benefits that organizations are able to derive from the
analysis of big data. Helps in decision-making, trend prediction, and
personalized recommendations.
Differences Between Traditional Data and Big Data:
Parameter Traditional Data Big Data
Data Size Limited (GBs to TBs) Vast (TBs to PBs or more)
Primarily structured data Structured, semi-structured,
Type
(rows, columns) and unstructured
Processing Speed Batch processing Real-time or near-real-time
Relational databases (e.g., Distributed systems (e.g.,
Storage
SQL) Hadoop, NoSQL)
Uses tools like RDBMS
Tools Hadoop, Spark, NoSQL
(MySQL, Oracle)
Limited (e.g., business Multiple (e.g., social media,
Scalability
transactions, logs) loT, sensors)
Predictive, real-time, and
Analysis Focus Historical data analysis
trend analysis
Cost-efficient with modern
Cost of Analysis Higher for large datasets
big data tools
Applications of Big Data
1. Healthcare: Enables predictive analytics for identifying health risks, personalizing
treatments, and improving diagnostics.
2. Retail and E-commerce: Analyze customer behavior for personalized shopping to
enhance recommendations and increase sales.
3. Finance and Banking: Detects fraud through real-time transaction monitoring.
Uses machine learning to flag suspicious activities, preventing unauthorized
access.
4. Transportation: Analyzes traffic to optimize routes, reduce congestion and provide
real-time traffic updates. Reduces delay and enhances road safety.
5. Media and Entertainment: Streaming platforms use big data to analyze viewing
habits and preferences, ensuring users receive personalized content
recommendations.
6. Education: Track student performance, identify learning gaps, and customize study
materials. This approach makes learning more effective and engaging.
7. Manufacturing: Track the performance of the equipment and predict potential
failure, which decreases downtime and maintenance costs. Sensors embedded in
machines collects data.
8. Government: Governments utilize big data to improve urban planning and optimize
resources, creating smarter and more sustainable cities.
9. Energy and Utilities: Energy providers use big data to analyze consumption
patterns, forecast demand, and improve energy efficiency. This helps in reducing
costs and promoting sustainability. Smart meters in homes collect data on
electricity usage and send it to utility companies.
10. Social media sites scan user-generated content such as posts, comments, and
tweets to understand public opinion and trends. This is very important for
businesses and policymakers.
Challenges in Data Analytics
1. Poor Data Quality: Data analytics often involves processing massive amounts of
raw data from multiple sources. This data may be incomplete, inconsistent, or
inaccurate, which can lead to poor-quality insights.

2. Data Integration: Data often comes from various sources and in different formats
like structured, semi-structured and unstructured, which makes integration
difficult. This incompatibility between systems can result in delays and incomplete
analysis.

3. High Resource Requirements: As the volume of data increases, processing and

storing it efficiently becomes a significant issue. Handling such petabytes of data
requires significant computational power, which can strain infrastructure.

4. Real-Time Processing Needs: Processing data in real-time for immediate insights

is difficult, especially with high-velocity data streams but delayed insights can lead
to missed opportunities in time-sensitive scenarios like fraud detection.
5. Data Privacy and Security Risks: Protecting sensitive data from breaches and
ensuring compliance with data protection regulations (e.g., GDPR, HIPAA) is
critical. Any data leaks can damage reputations and result in legal penalties.

6. Lack of Skilled Professionals: There is a growing demand for data scientists,

analysts and engineers, but a shortage of skilled professionals who can analyze
and interpret complex data.