Course Outline

Introduction to
Marketing Business
Analytics
By Prof. Manisha Kapoor
 Ensure that –
Live session 1. You have renamed your name in the
following format - “Enrolment ID_Name” For
etiquette Example: “19BSP1761_Anjali Mathur”.
2. You are on mute.
3. You have turned-off your video.
4. You use chat in-case you have any question.
Snapshot : Course Syllabus
Course
Objective
Data driven insights that can
benefit business firms
Learning Outcomes :
Marketing Business Analytics

• To equip students with an understanding of

the “importance and role of marketing
analytics” in modern business enterprises
and how business firms can take advantage
of marketing analytics.

• Further for students who wish to specialize

in analytics, the course provides a strong
foundation in the application of marketing
analytics with analytical platforms.
Tools
Agenda

WHY WHAT HOW

BENEFIT DATA ANALYTICS
 Data Exploration
Data Summarization
Cross Tabulations
Slicing and Visualisation
Dicing of Conversion Numeric to Categorical
Data Renaming Factor Levels
Standardizing/Scaling data
Handling Missing values
 Modelling Modelling
perceptions choices
Customer Analytics :
Understanding Consumers

Segmenting
Consumers
 1

Perceptual
Mapping
Low Fashion High Fashion

How my brand is
perceived by
customers ?
 How I am What messages I
Where I want to
currently need to
position ?
positioned ? emphasize ?
 How I am positioned vis a vis competition?

What are my strengths and weaknesses?

Who all are my close competitors?

Benefits Am I differentiated ?

Is there any current gap in the market ? – new product & existing
product

What is my ideal point?

If I want to shift myself to my ideal point/market leader what

strategy /changes in positioning messages I need to make ?
Modelling Consumer Perceptions : Factor analysis

• A perceptual map enables the marketing

analyst to determine how a product
perceived compared to the competition so
that they can can (re) position them
appropriately.
• When a perceptual map of products or
brands is available, the marketing analyst
can use an individual’s ranking of products
to find the individual’s ideal point or most-
wanted location on perceptual map

High Fashion • Perceptual Mapping

• Brand rating Data
• Cars Dataset
 PCA in R : Visualization outputs

Heat Map
Scree plot Correlation Plot
 Fun
This is one outcome of perceptual map of
brand rating data that has been plotted by
doing factor analysis in R.
Here a, b, c, d, e, f, g, h, I, j are brands.

Latest Value

Suppose you are a manager of brand e. What does the

map tell you? How your brand is perceived? Whether
the brand is differentiated? What is the ideal point?
What should you do about the position of your brand
e? what messages the brands need to emphasize?

Leader
If the brand is positioned on it’s ideal point it can drive profits
 Why - Positioning
BENEFIT

Why, What
and How – What - Brand Perception data
Perceptual DATA
Mapping
How - Factor analysis and
perceptual maps
ANALYTICS
 2

MARKET
SEGMENTATION
Whom should I
target ?
Market Segmentation : Cluster analysis

• Market segmentation is breaking

the market into distinct subsets
of customers
• Market Segmentation
• Cluster Analysis
• Shopping Data
• Cars Dataset
SEGMENTATION
BASICS
Case
Studies
CUSTOMER PROFILES
 Why - Identify right customers
BENEFIT

Why, What
and How – What – Segment profiles
(Segmenting and Targeting
Market DATA
variables data)
Segmentation
How - Cluster analysis
ANALYTICS
 3

MODELLING
CONSUMER
CHOICES
Whether
customer will
buy my brand or
not ?
Modelling Consumer Choices : Logistic Regression

• How do consumers choose which brand to

buy from a choice set?
• What determines whether a consumer
renews a contract or churns?
• Consumer choice modeling
• Logistic Regression
• RFM purchase decision dataset
• Amusement park dataset
Classification problem : Logistic
Regression
 What types of classification problems can we answer using Logistic
Regression?

Sector/Domain Problem Statement

HEALTHCARE Whether a person will have diabetes or not?
Whether a medicine will cure the disease or not?
BANKING Whether a customer will default on it’s loan or not?
MARKETING Whether a person will purchase or not?
Whether a person will churn or not?
Whether a customer will respond to marketing activities?
HUMAN RESOURCES Identifying the employees most likely to get promoted?
OTHER EXAMPLES Whether a mail is spam or not?
 • Purchase (Buy/not buy)
Why • Response to marketing efforts
• Predict churn before it happens
BENEFIT

Why, What
and How – What - Data of customers who
have purchased in past (Historical data)
Logistic DATA
Regression
How – Logistic Regression
ANALYTICS
 4

Customer
Lifetime Value
What is the
value of a
customer ?
Customer centric models : Modelling CLV

• CLV is the net present value of

all future streams of profits that
is generated by a customer over
the duration of the relationship
with the firm.

• Customer Acquisition
• Customer Retention
• Customer Expansion
 • Optimize acquisition cost (more
customers and reduce
Why acquisition cost)
• Increase profitability of customer
BENEFIT ( increase share of wallet and
buys more)
• Increase retention rate
Why, What
What – Retention rate and
and How – profit pattern
CLV DATA

How – CUSTOMER LIFETIME

VALUE FORMULA
ANALYTICS
Recency
Frequency
Monetary
Value
Who are my
loyal/lost
customers ?
Customer centric models : RFM Analysis

• RFM analysis starts by basically asking three

questions about each customers.
1. How recently they have shopped with
you?
2. How often do they make a purchase?
3. How much have they spent?
• Through RFM analysis, you can rank your
customers into categories to find your most
loyal customers, those who are more at risk,
or, for example, those who haven’t shopped
recently.
• RFM Analysis
• Segmentation based on RFM data
• Online Retail Transaction data (Kaggle)
 RFM Score = Recency Score*100 + Frequency
SEGMENTS Score *10 + Monetary Score
 • Organize customer
databases into specific
Why segments.
BENEFIT • Type of marketing to use
to target segments

Why, What
and How – What – RFM Data (Historical transactional
data)

RFM Analysis DATA

How – Segmentation based on

RFM
ANALYTICS
 • RFM analysis is used to organize customer databases
into specific segments. Basing these segments off
customer’s purchase behavior gives crucial insight
into the type of marketing you should use to target
them and to move them between segments.
• Frequency and Monetary value are core to
calculating your customer lifetime value (CLV) ;
RFM and CLV meanwhile, recency gives insight into customer
engagement and indicates the likelihood of that
customer coming back again.
• Targeting your marketing based on these metrics
allow you to focus your budget on areas such as
retention and acquisition, while still moving
customers to more reliable segments
Market Basket
Analysis
What product
will my
customer buy ?
Imagine you go to super market to buy Bread. What
are the other items that are likely to land in your
basket other than bread?

Can you think of items

that are bought together?
Basics of Association rules : Example

For example, consider sales of bread and eggs. Imagine that breads are sold in 5% of
supermarket transactions during a month, while eggs are sold in 3% of transactions.

Are they related?

 Evidence of association

• Suppose we just take the data for every sale that includes bread, which is 5% of
transactions. If the proportion of those bread sales that have eggs is 3%, then there is no
relationship because that is what we would expect for eggs from the overall data,
regardless of what else is sold. However, if eggs are sold in 25% of the transactions that
have bread, that is quite different than the base rate and is evidence of an association.
Retail Analytics : Market Basket Analysis

• Market Basket Analysis is one of the

key techniques used by large
retailers to uncover associations
between items
• Market Basket can be used in
deciding the location and promotion
of goods inside a store
• Market Basket Analysis
• Association rule mining
• Groceries dataset
 Applications

• Product recommendation
• Recommend movies – Netflix
• Recommend products - Amazon
• Store layout
• Sales promotion
 Why - Decide the location and
promotion of goods inside a
store
BENEFIT

Why, What
and How – What – Retail Transactional
data / Receipts /Bills
Market Basket DATA
(List of items that are purchased together)

Analysis
How - Association rule mining
(conditional probability)
ANALYTICS
Advertising
Analytics
How much
should I spend
on
advertisement ?
Advertisements

• Companies spend money on

advertising to impact sales
• Modelling the sales response
function
• Computing the causal impact of
advertising
Interaction effect !
 Why - Decide the impact of
advertisement on sales
BENEFIT

Why, What
and How – What – Advertisement and
sales data
Advertising DATA
(L)

Analytics
How – Regression Analysis
ANALYTICS
Sales
Promotion
What is the net
impact of sales
promotions ?
Sales Promotion

• Sales promotions are short

term inducements designed
to have a direct impact on
the buying behavior of end
users and trade
• Assessing the profitability
of sales promotions
• Modelling incremental
sales
Modelling the increment of impact of promotion

TREND SEASONALITY WAITING FOR STOCKPILING

PROMOTION
 Why - Decide the impact of
promotion on sales
BENEFIT

Why, What
and How – What – Promotion and sales
data
Sales DATA
(Trend, seasonality)

Promotions
How – Regression Analysis
ANALYTICS
Pricing
Analytics
How much
should I price
my product ?
Pricing Analytics

• Modeling Willingness to
Pay
• Modeling Demand Curves
• Optimal Pricing
• Pricing strategies (Price
skimming, Price bundling)
• B2B dataset
 Why – Optimize price
BENEFIT

Why, What
and How – What – Willingness to pay data
Pricing DATA
Analytics
How – Normal Distribution &
Logistic Regression distribution
ANALYTICS
Social Media
Analytics
Customer
sentiments
towards my
product
Social Media Analytics : Sentiment Analysis

• Social media is gradually being

recognized as a significant resource for
understanding customer sentiments,
the reputation of products, willingness
to buy, and customer satisfaction with
products and/or services.
• Social media analytics in hospitality
and tourism/film industry/mobile
companies
• Social Media Analytics
• Text mining & Sentiment Analysis
Strategy
Strategy

• How managers can

use marketing mix models to guide
their decision making
• Marketing Planning and Strategy
Decisions, Managing the Marketing
Mix
 Grading : Continuous
Evaluation
Evaluation Batch of Allocation Batch of
Component
2021 2021
Online Evaluation :
C1 Quizzes, Forums, 100 Marks (15%)
Assignments

C2 Mid-term Exam 100 Marks (20%)

C3 Group Project 100 Marks (15%)

Class participation and

C4 100 Marks (10%)
attendance**

C5 End-Term Exam 100 Marks (40%)

 Session Plan : 1/4

Number of
Session No Topic Details
Sessions
Introduction to Marketing
S1 1 Understand Marketing Business Analytics and it's application
Business Analytics
Data types, lists , factors, vectors, Matrices, data frame, slicing and
dicing of data, functions, packages and library, Report writing in R
S2-S4 R Tutorial 3 Markdown, Descriptive Analysis, Visualization, Chi square, Correlation,
Regression
What is Segmentation, Why Segment, Benefits of segmentation to
firm and customers, Bases/Types of Segmentation, Segmentation
S5-S7 Market Segmentation 3 Methods - Cluster Analysis - Hierarchical and K-means, Segment
Profiling, Strategy - Marketing Mix
Consumer perception towards brand and product offering, Factor
S8-S10 Perceptual Mapping 3 analysis and Perceptual maps, Applications – Positioning, Competitive
Analysis, Identifying competitive advantage, Positioning Strategy
Linear and Multiple
S11-S12 2 Regression basics
Regression
 Session Plan : 2/4

Number of
Session No Topic Details
Sessions
C1 (Quiz based on coding assignment) 100 Marks (15%)
Modelling consumer Consumer choice behavior, Logistic Regression, Use of choice
S13-S15 choices 3 modelling in marketing

S16 CLV Formula 1 Margin multiple calculation

C2 (Mid-term Exam) 100 Marks (20%)

Customer Lifetime Value (CLV ) & Recency, Frequency, Monetary Value

S17-S18 Customer centric Models 2 (RFM)
 Session Plan : 3/4

Number of
Session No Topic Details
Sessions
S19 Advertisements 1 Linear and Multiple Regression

Sales Promotions Linear and Multiple Regression

S20 1

Retail Analytics Market Basket Analysis, Association rules mining

S21-S22 2

S23-S25 Group Projects 3

Pricing WTP, Pricing of new products, Optimize price and

S26-S28 3
Analytics profits
 Session Plan : 4/4

Number of
Session No Topic Details
Sessions
S29 Social Media Analytics 1 Theoretical

S30 Strategy 1 Theoretical

End-Term 100 Marks

(40%)
 Next Session
• R Tutorial
• Ensure that you have installed R and R studio
• Download R Markdown file that is provided to you under the topic
session 2 on quicforce MBA course page.
Thank you