Chapter 1:

Introduction to Business Analytics

What is Business Analytics?

Analytics is the use of:

data,
information technology,
statistical analysis,
quantitative methods, and
mathematical or computer-based models
to help managers gain improved insight about
their business operations and make better,
fact-based decisions.
 Analytics is the scientific process of converting
raw data into knowledge to support decision
making.
 Analytics involves finding trends & patterns in

data.
 The goal of Analytics is to improve business,

society or personal performance by gaining

knowledge from data.
 Analytics is moving decision making from Gut feel

and guesstimates to better, more informed ones

driven by data.
What is Business Analytics?

Importance of Business Analytics

 There is a strong relationship of BA with:

- profitability of businesses
- revenue of businesses
- shareholder return
 BA enhances understanding of data
 BA is vital for businesses to remain competitive
 BA enables creation of informative reports
About Data:
 Data is growing at 40% compound annual rate
reaching by 45ZB by 2020
 2.5 Quintillion bytes of data created each yr.
 90% of data in world was created in last 2 yr.
 Why is Analytics is USED

◦ Design making is now fact and performance based.

◦ Intuition is out, metrics are in.
◦ Shorter time to market, demanding customer.
◦ Make each and every dollar count and increase return on
investment.
◦ Faster, better decision making
What The Market Buzz On Analytics

 Business Analytics Market is estimated at $44.5 billion in 2015 and

is expected to reach $71.1 billion by 2022 growing at a CAGR of
6.9% from 2015 to 2022.
 83% business leaders globally identified as their top priority-IBM
 Shortage of 1.5mn business analytics professional by 2020-
McKinsey
 India has become a global analytic hub-Times of India
 The next big job boom is in analytics-up to 250k job openings in
analytics over next 2 yrs. starting salaries to be in range of Rs 5-
9lacs PA-DNA
 Indian companies grooming data scientists to feed global jobs
demand-Business Today
Key Business analytics tools
 Unmet need analytics
◦ Uncover any unmet needs around your product or service or
within your market which increase customer satisfaction and
revenue.
◦ E.g. product reviews, qualitative surveys, focus groups and
interviews.
 Non-customer analytics
◦ Non-customer analytics is about understanding what people who
are currently not your customers think about your product,
services or brand.
◦ By identifying who is not buying from you (and why), you can
expand your market to include those individuals.
Key Business analytics tools
 Market size analytics
◦ Helps to understand the size and growth potential of your market
and analyze viable business proposition
◦ The size of the market is measured in terms of volume (how
many units sold), value (money spent in that market) or frequency
(how often a product or service is sold).
◦ Useful data includes government data, trade association data,
financial data from competitors, and customer surveys.
 Market trend analytics
◦ Helps to know the direction the market is heading
◦ Establish whether a market is growing, stagnant or in decline and
how fast that movement is occurring.
◦ To monitor market trends you can run business experiments or
scenario analysis also customer surveys and focus groups.
Uses of Analytics
 Marketing  Retail Analytics
◦ Customer Segmentation ◦ Shelf space allocation
◦ Analysis of customers preference
◦ Up Selling/Cross Selling
for store brand or brand names
◦ Market Basket Analytics ◦ Pricing decisions
◦ Marketing Media Mix Analysis ◦ Promotions and product bundle
 Financial Sector offerings

◦ Credit Risk Management

 Media Analytics
◦ Credit Scorecard Modeling ◦ Decision making on allocation of
air- time of a new TV show
◦ Fraud Detection ◦ Prime time rate for advertisement
◦ Stock Market Analysis ◦ Analysis of channel viewership
Evolution of Business Analytics

 Operations research
 Management science
 Business intelligence
 Decision support systems
 Personal computer software
COMPETING ON ANALYTICS –
THE NEW SCIENCE OF WINNING
 ANALYTICS TUNES THE
BEST COMPANIES IN THE
WORLD
SOME OF THEM ARE AS
FOLLOWS…
P&G APPLY CRITICAL MASS
OF EXPERTISE TO ITS MOST
PRESSING ISSUES WITH ITS
UBERANALYTICS GROUP
CONSISTING OF MORE THAN
100 ANALYSTS
’
=

+
Competing on Analytics - The New
Science of Winning
 Right focus
 Right Culture
 Right People
 Right Technology
Types of Analytics
Types of Data Analysis

Descripti Predictiv Prescriptiv

ve e e
• Aims to help • Helps forecast • Suggests
uncover valuable behavior of conclusions or
insight from the people and actions that
data being markets may be taken
analyzed • Answers the based on the
• Answers question analysis
the “What could • Answers the
question happen?” question
“What “What
happened? should be
” done?”
Descriptive Analytics
 The conventional form of Business Intelligence
and data analysis. It answers the question “What
has happened?”
 Provide a depiction or “summary view” of facts

and figures( past as well as present) in an

understandable format, to either inform or prepare
data for further analysis.
 It uses two primary techniques, namely data

aggregation and data mining to report past events.

 It rarely attempts to investigate or establish cause

and effect relationships

 Descripti Data Analytics
ve
Mean, Median and Mode
 Though the most simple type, it is used Amounts of Items Purchased
most often.
6.5
 Two types of descriptive analysis: 7
1. Measures of central tendency (tells 6
us about the middle) 5
 Mean − the average 4
 Median − the midpoint of 3
the responses 2
 Mode − the response with the 1 2
highest frequency 0
1
2. Measures of dispersion
 distance between
Range − the the max
min, the two and the
 Variance − the average degree to Mean Median Mode
which each of the points differ from
the mean
 Standard Deviation − the most
common/standard way of Customer_ID Items Purchased Amount Spent
expressing the spread of data
29304 1 1.09
28308 3 44.43
19962 21 218.58
30281 1 73.02
Descriptive Analytics: Excel & Power BI

 Key task: Data access / shaping – Power

Query does this
 Excel + Power Pivot data model holds Past
Business Results
 Pivot charts, Power View, Power BI for data
visualization
 Formulas: Sum, Count, Average, Min, Max,
Var, StdDev

35
 Predictive Data Analytics

 Analyze past data patterns, trends and accurately inform a business

about what could happen in the future.
 This helps in setting realistic goals for the business, effective
planning and restraining expectations.
 Predictive analytics is used by businesses to find answers to the
question “What could happen in the future based on previous trends
and patterns?”
 Predictive analytics can only forecast what might happen in the
future, because all predictive analytics are probabilistic in nature."
 Uses various data, statistical and machine learning algorithms to
forecast but the accuracy of predictions is not 100%, as it is based
on probabilities.
 Several of the models that can be used for predictive analysis are:
− Forecasting , Simulation, Regression, Classification, Clustering
Predictive Analytics: Data Mining
 Key tasks: Data shaping, applying predictive models
 Data mining algorithms “fit” analytic model to past data
 Trained/fitted models are applied to newly arriving data
◦ Classify: ex. Good/Poor credit risk, Likely/Unlikely to churn
◦ Predict: ex. stock price, house price, exchange rate
◦ Forecast a time series: ex. next sales from past sales history
◦ Associate: ex. People who bought this item also bought...

 Tools: Azure ML, XLMiner, Predixion, SAS, SPSS, R, others

37
 Predictiv Forecastin
e g
 Forecasting:
− Moving average technique: use the Net Income of Store C Projected 2017-
mean of prior periods to predict 2020
the next $25,000.00

 The mean of periods 1−4 = period

5 $20,000.00
 The mean of periods 2−5 = period
6 $15,000.00

− Exponential smoothing technique:

similar, but more recent data $10,000.00

points are weighted more heavily

due to relevance $5,000.00

− Regression techniques
 Use caution in forecasting – The $-

larger the forecasted time 2006 2008 2010 2012 2014 2016 2018 2020 2022

period, the less accuracy there

is in the projections.
 Predictiv Simulatio
e n

 Simulation
− Queuing models: used to predict wait time and queue
length
 Results can be used to create staff schedules in a way that reduces
inefficiencies, etc.
− Discrete event model: used in special situations when
queuing cannot be used
 Results can be used to identify bottlenecks, etc.
− Monte Carlo simulations: used to identify probable
outcomes of a scenario based on many possible
outcomes (uses random number generation and many
iterations of the scenario).
 Results can be used to predict the likelihood of profitability
within the first two years, etc.
 Predictiv Queuing Model
e Example

Scenario Scenario
1 2
 Predictiv Classification &
e Clustering
 Classification: used to assign objects
to one of several categories
− Sentiment analysis of social
media postings
 Clustering: another method of
forming groups
− Intragroup differences are minimized
− Intergroup differences are maximized
− Commonly used to create and
better understand customer
groups
 Prescriptiv Data
e Analytics
• Prescriptive analytics is the next step of predictive analytics that
adds the spice of manipulating the future.
• Prescriptive analytics advises on possible outcomes and results in
actions that are likely to maximise key business metrics.
• It basically uses simulation and optimization to ask “What should
a business do?” 
• Prescriptive analytics is an advanced analytics concept based on
Optimization that helps achieve the best outcomes.
• Stochastic optimization that helps understand how to achieve the
best outcome and identify data uncertainties to make better
decisions.
 However, prescriptive analytics explicitly tell you the decisions that
should be made. This can be done using a variety of techniques:
− Linear programming
− Integer programming
− Mixed integer programming
− Nonlinear programming
Prescriptive Analytics: Optimization,
Simulation
 Key task: Create a model – A person (you) must do this
◦ Model must capture essential features of the business
situation
◦ Larger models often get their data from BI / Descriptive
Analytics
◦ A “What If” model is the starting point – Excel is a natural
tool!

 Given an appropriate model, we can:

◦ Ask “What are all the possible outcomes?” – simulation/risk
analysis
◦ Ask “What’s the best outcome we can achieve?” –
optimization

 Tools: Solver, Risk Solver, @RISK, Crystal Ball, IBM, SAS,

others
43
Comparing the Three Types of Data
Analytics
 Descriptive analysis is most common.
− Best practice to perform descriptive
analyses prior to
prescriptive/predictive
 Understand that distribution,
variance, skew, etc., may exclude
certain models
 How to know which type of analysis
to pursue:
− How much time do you have?
− What resources are available to you?
− How accurate is your data? How
accurate do you need the
model/analysis to be?
− How popular/accepted is the model you
are considering?
 Don’t subscribe to “that’s how we’ve always done it,”
but remember to use a model that stakeholders will
accept.

[Link]
Scope of Business Analytics
 Descriptive analytics
- uses data to understand past and present
 Predictive analytics

- analyzes past performance

 Prescriptive analytics

- uses optimization techniques

Scope of Business Analytics

Example 1.1 Retail Markdown Decisions

 Most department stores clear seasonal inventory

by reducing prices.
 The question is:

When to reduce the price and by how much?

 Descriptive analytics: examine historical data for
similar products (prices, units sold, advertising, …)
 Predictive analytics: predict sales based on price
 Prescriptive analytics: find the best sets of pricing

and advertising to maximize sales revenue

Data for Business Analytics
 DATA
- collected facts and figures
 DATABASE

- collection of computer files containing data

 INFORMATION

- comes from analyzing data

Data for Business Analytics

Examples of using DATA in business:

 Annual reports
 Accounting audits
 Financial profitability analysis
 Economic trends
 Marketing research
 Operations management performance
 Human resource measurements
Types of Data

(Categorical) (Measurement)
Categorical Data
 The objects being studied are grouped into categories
based on some qualitative trait.
 The resulting data are merely labels or
categories.
 Examples: Categorical Data
• Hair color
 blonde, brown, red, black, etc.
• Smoking status
 smoker, non-smoker
Data for Business Analytics

Categorical (nominal) Data

 Data placed in categories according to a specified

characteristic
 Categories bear no quantitative relationship to one

another
 Examples:

- customer’s location (America, Europe, Asia)

- employee classification (manager, supervisor,
associate)
Data for Business Analytics

Ordinal Data
 Data that is ranked or ordered according to some

relationship with one another

 No fixed units of measurement
 Examples:

- college football rankings

- survey responses
(poor, average, good, very good, excellent)
Binary Data
Binary Data
 A type of categorical data in which there are only two

categories.
 Binary data can either be nominal or ordinal.
 Examples: Binary Data
• Smoking status
 smoker, non-smoker
• Attendance
 present, absent
Measurement Data
 The objects being studied are “measured” based on
some quantitative trait.
 The resulting data are set of numbers.
 Examples: Measurement Data
• Cholesterol level
• Height
• Age
• CAT score
• Number of students late for class
• Time to complete a homework assignment
Measurement Data
 Discrete Measurement Data
◦ Only certain values are possible (there are gaps between the
possible values).
• Examples: Discrete Measurement Data
 Number of students late for class
 Number of times the word number is used
Continuous Measurement Data
◦ Theoretically, any value within an interval is possible with a
fine enough measuring device.
• Examples: Discrete Measurement Data
 Cholesterol level
 Height
 Age
Discrete data -- Gaps between possible
values

0 1 2 3 4 5 6 7
Continuous data -- Theoretically,
no gaps between possible values

0 1000
Data for Business Analytics

Interval Data
 Defined as a data type which is measured along a

scale, in which each point is placed at equal distance

from one another. Interval data always appears in the
form of numbers or numerical values where the distance
between the two points is standardized and equal
 No true zero point
 Ratios are not meaningful
 Examples:

- temperature readings
- CAT scores
Data for Business Analytics

Ratio Data
 Continuous values and have a natural zero point
 Ratios are meaningful
 Examples:

- monthly sales
- delivery times
Data for Business Analytics

Example 1.2 A Sales Transaction Database File

Records

Figure 1.1

Entities Fields or Attributes

Data for Business Analytics

Example 1.3
Classifying Data Elements in a Purchasing Database

Figure 1.2
 Data for Business Analytics

Example 1.3 (continued)

Classifying Data Elements in a Purchasing Database

Figure 1.2
C

C
C

R
R
R

In
In
at

at

at
at

at

at
at
at

te
te
eg

eg

eg
eg l

io

io
io
io

rv
rv
or

or

or
or

al
al
ic

ic

ic
ic
al

al
al
Business Analytics –- The Paradigm
Shift from Data to Insight
 Business analytics alter the approach of decision
making, apply analytical techniques to data in
order to create insightful and efficient resolutions to
everyday business issues and to create value.
 Paradigm shift is from intuition driven decision

making to data driven, computer assisted

decision making
 Cognitive psychology says that humans are

susceptible to illusion of memory & illusion of

knowledge(i.e. believing that our memories are
accurate & our knowledge is correct) & therefore
prone to serious inaccuracies & error.
 Business Analytics –- The Paradigm
Shift from Data to Insight
Data provides accurate documentation of the past.
Such documentation improves awareness, enhance
understanding and better decision making.
Data information Knowledge intelligence
 Generating insights from data requires transforming the

data in its raw form into information that is

comprehensible to humans
 One should dive even deeper by asking “Do you know

what you do not know” i.e. is there any insight that is

hidden within the wealth of data that can improve
business process, uncover growth
Thank you