Marketing Analytics

Welcome
Session-I
Data, Information, Knowledge:
What’s the difference?
Marketing Vs. Data OR
Marketing + Data
Increasing Interest in Massive Data
 Business Analytics - Definition
Business analytics (BA) refers to the tools, techniques
and processes for continuous exploration and
investigation of past data to gain insights and help in
decision making and problem solving.

Business Analytics is an integration between

business/problem context, technology and data
science that assist data driven decision
making/problem solving.
 What is Marketing Analytics
• Marketing analytics is the practice of measuring, managing and
analyzing marketing performance to maximize its effectiveness
and optimize return on investment (ROI)
• Beyond the obvious sales and lead generation applications,
marketing analytics can offer profound insights into customer
preferences and trends
• Despite these compelling benefits, a majority of organizations
fail to ever realize the promises of marketing analytics
• According to a survey of senior marketing executives published
in the Harvard Business Review, "more than 80% of respondents
were dissatisfied with their ability to measure marketing ROI"
WHY ANALYTICS…???

Competitive
Strategy
Data is
everything
Decision Making
(What promotion Strategy to use)

Problem Solver
(Optimal Product Mix)

Process Improvement
(Reduce procurement cycle time)
In God we trust, all others must bring
data
- W Edwards Deming
 Analytics for Process Improvement

• Banking – Cheque clearance time

• Healthcare – Patient discharge time

• Manufacturing – Waste minimization

• Retail – Waiting time at check out counters

• E-commerce – Time to deliver the customer order

 Analytics for Problem Solving
• Banking – Reduce non-performing assets, Predict Fraud

• Healthcare – Improve net promoter’s score (NPS)

• Manufacturing – Reduce inventory management cost

• Retail – Assortment planning and shelf space allocation

• E-commerce – Predict customer cancellations and Fraud

 Analytics for Decision Making
• Banking – Loan approval and the interest rate

• Healthcare – Introducing new specialties

• Manufacturing – Whether to introduce a new product

• Retail – Markdown Pricing

• E-commerce – Promotions
Analytics is necessary for survival
Problems faced by E-commerce companies such as Amazon and
Flipkart
• Forecast demand for each SKU.

• Predict customer cancellations and returns.

• Predict customer contacts at the customer service.

• Predict what a customer is likely to purchase in the

future?

• How to optimize the delivery system?

 The Game Changers…
• Google
– Used Markov chains to rank pages
• Proctor and Gamble
– Analytics as competitive strategy.
• Target
– Predicts customer pregnancy.
• Capital One
– Identifies the most profitable customer.
• Hewlett Packard
– Developed “flight risk score” for 3,30,000 employees.
• Obama’s 2012 presidential campaign.
– Persuasion Modelling.
 The Innovators…

• OKCupid: Predicts which online dating messages is most likely to

get a response!

• Polyphonic HMI: Uses “hit song science” to predict commercial

success of a song.

• Netflix: Predicts movie ratings by customers (RMSE is 1%).

• Amazon.com: 35% of sales come from product recommendations.

• Divorce360.com: Predicting success of a marriage!

 The scenario in India
• Overall assessment
• Nascent domain but lots of excitement
• Does not have a strong independent academic research foundation
• Hence, most of the work is practice-centric (external validity is very important)

• What is practice
• Overwhelmingly, dominated by offshore work which is largely technology –
methodology based.
• Methods / Automation to improve efficiency
• Domestic sector exhibits spotty attempts at imbibing Analytics for decision making
(IIMA working paper series – 2014-12-07)
• Data incomplete and spotty
• Data in many incompatible formats
• Market opportunities remain extensive for growth without need for precision
• Unpenetrated market has little data to support scientific analysis
• Organizations are developed to manage in data-scarce environments
• “See I told you so” attitude
 The scenario in India
• Winds of change
• Slowing down of markets in recent times
• Global movement of talent / methods in Analytics and influx in India
• Realization that data exist and has value (more than zero)
• Motivation – can we use it?

• Complication – How / where to begin?

• Most evolved experts in the global Analytics space “teach” methods
• How to deploy the methods in a nascent environment with scattered data
• Need to first build a data ecosystem that facilitates use of methods
• But having a strategic data organization plan with identified scope for
subsequent analysis is useful
 Components of Analytics

Predicting future
Data synthesis and events
Visualization
Descriptive Analytics Predictive Analytics

Prescriptive Analytics

Optimization and decision

making
 Components of Analytics

Descriptive Predictive Prescriptive

Analytics Analytics Analytics

What Happened ? What Will Happen ? What Action to Take ?

 Big Data

• Big data refers to high volume of data generated

at high velocity that contains large variety of data.

• According to Gartner Report, data is classified as

big data, when:
– Volume: Exabytes
– Velocity: Sub-second
– Variety: 25+ formats
– Veracity: Accuracy of the data
 Sources of Big Data

• Transactional data that are generated at high speed (mobile

services, banking and financial services, healthcare,
entertainment, etc.)

• Machine generated data (electricity and water meters, sensors

installed in various systems).

• Social media data.

• Machine generated unstructured data (videos, satellite images

etc).
 4 BINS OF ANALYTICS PROBLEMS

Prediction Classification Matching Optimization

Forecasting Customer Fingerprint Vehicle Routing

Churn matching
Customer Bin-packing
lifetime Credit Risk Recommender
value Systems
‘Big Data’ Hype
‘Big Data’ Hype: Competitive advantage from
big data is declining

MIT SMR Research Report “Beyond the Hype: The Hard Work Behind Analytics Success”, March 2016
Broken Links in Information Value Chain

MIT SMR Research Report “Beyond the Hype: The Hard Work Behind Analytics Success”, March 2016
More data but less impact on strategy

MIT SMR Research Report “Beyond the Hype: The Hard Work Behind Analytics Success”, March 2016
 FRAMEWORK- DATA-DRIVEN DECISION MAKING

Problem or Opportunity Identification

●
Domain knowledge is very important at this stage of the analytics project.
●
This will be a major challenge for many companies who do not know the capabilities of analytics.

Collection of relevant data

●
Once the problem is defined clearly, the project team should identify and collect the relevant data.
●
This may be an interactive process since "relevant data" may not be known in advance in many analytics projects.
●
The existence of ERP systems will be very useful at this stage.

Data Pre-processing

●
Data preparation and data processing forms a significant proportion of any analytics project. T
●
his would include data imputation and the creation of additional variables such as interaction variables and dummy variables in the case of predictive analytics projects.

Model Building

●
Analytics model building is an iterative process that aims to find the best model.
●
Several analytical tools and solution procedures will be used to find the best analytical model in this stage.

Communication and deployment of the data analysis

●
The communication of the analytics output to the top management and clients plays a crucial role.
●
Deploy the solution
Decision Making…..how do we do it with Analytics??

- CONSULTANT

E = mc ± ∆ 2

CONTEXTUAL
DECISION SCIENTIFIC CLARITY
FAMILIARITY

Taking better decisions requires

• Get Better at Anticipating and Manipulating Environment (some thru Analytic
Insights
• Get Better at assessing the “error” portion of the science(being realistic about the
limitations of and leakages in Analytical Decision models and looking for “opps”
to improve them )
 Extracting value from the data

Data Statistical models & Machine

Learning Algorithms
Science

Business
Context

Problems, Opportunities, Data collection, storage,

Decision Scenarios retrieval Software tools

Technology
Agenda

4. Analytic Priorities across

Multiple Contexts

3. Tool Box Appreciation

2. Model
Formulation

1. Context Setting and Getting Started

 So, what are the capabilities required to add value to
Decision Making through Analytics?

Required capabilities are on three separate dimensions with significant crossover

1 2
ANALYTIC PROCESSING /
INFORMATION PROGRAM
MING ANALYTICS PROWESS
ARCHITECTURE &
MANAGEMENT 4 MODEL
DATA BUILDING
COLLECTION NO TRAINING PROGRAM
/ RETRIEVAL
PROVIDES INPUTS IN
PLAN
3
ALL THREE AREAS
BUSINESS
ACUMEN
Embedded Analytics
Organization
 Intelligence through Analytics
4

Optimization
What will happen next?
Predictive Modeling
What is the best that can
happen?
1,2
Forecasting What happens if the trend continues?
Competitive Advantage

Statistical Analysis
Why is this happening?
Alerts
1 What actions are needed?

Query drill downs

where exactly is the problem?

Ad hoc reports
How many, how often, where?

Standard reports
What happened?

Degree of Intelligence
Agenda

4. Analytic Priorities across

Multiple Contexts

3. Tool Box Appreciation

2. Model
Formulation

1. Context Setting and Application Focus

 Model Formulation
• Usually a template of a phenomenon to be studied

• In practice, what phenomenon to be studies is to be

appropriately selected basis the business problem
to be solved

• The above has no association with the statistical

tool box to be used – can be selected much later

• We will discuss a case to illustrate this point

 The 360o view of the customer
What is she thinking ?

What is she going to do ?

Who is she ?
What is she seeing ?
Ideally, we would like to link them all…..
Modeling Caveats
• Each business is a unique blend of key “levers”
and each market is different.
• Models are predictive in as much as historical
performance is similar to what will be executed
in the future.
• Models are not a substitute for sound marketing
/ business judgment.
• Model results are not fixed over time.
• Model results require a qualitative validation
with contextual realities
Agenda

4. Analytic Priorities across

Multiple Contexts

3. Tool Box Appreciation

2. Model
Formulation

1. Context Setting and Application Focus

CRM & Marketing Analytics Software
Data Analytics Software
Agenda

4. Analytic Priorities across

Multiple Contexts

3. Tool Box Appreciation

2. Model
Formulation

1. Context Setting and Application Focus

Railroad Laundry Service
 FRAMEWORK- DATA-DRIVEN DECISION MAKING

Problem or Opportunity Identification

●
Domain knowledge is very important at this stage of the analytics project.
●
This will be a major challenge for many companies who do not know the capabilities of analytics.

Collection of relevant data

●
Once the problem is defined clearly, the project team should identify and collect the relevant data.
●
This may be an interactive process since "relevant data" may not be known in advance in many analytics projects.
●
The existence of ERP systems will be very useful at this stage.

Data Pre-processing

●
Data preparation and data processing forms a significant proportion of any analytics project. T
●
his would include data imputation and the creation of additional variables such as interaction variables and dummy variables in the case of predictive analytics projects.

Model Building

●
Analytics model building is an iterative process that aims to find the best model.
●
Several analytical tools and solution procedures will be used to find the best analytical model in this stage.

Communication and deployment of the data analysis

●
The communication of the analytics output to the top management and clients plays a crucial role.
●
Deploy the solution
 Back to the Basics of Research Planning – Railroad Laundry
Sources of Info
Sub Decision Problem RQs
• Primary Data
• Can we describe them?
• How is their lifestyle? Collection
• Observational
Whom to Target • What do they miss out on?
•Where do they live? Survey
• Neighbourhood
• What is the size of the TG?
Census Data

Objective Decision Problem • What can we help them with?

• Primary Data Collection
• What is the description of the
• Competitor Scrutiny
service? • Expert Interview
What to offer • What are the critical parameters to
Break Even in What is the
maintain?
Yr. 1 Service • Can we monetize the value of this
USD 1.5 Opportunit service? How much?
Million in y?
Yr. 2 Define the • Can we describe the • Expert Advice
operational layout for this • Public Records
10% Net Value
Is this viable and how service? • Primary Data and
Profitability Proposition •What are the major cost Census for Demand
heads? Projection
•What would be the • BE Analysis
demand projection? Framework
•Communication/Servicin
g Objective?
Problem Solving Begins • Can we identify points of

here
differences?
Do we need to combat • What would be a potential • Intelligence Reports
Competition and how? competitive reaction? • Observations
• How will that affect our • Primary Customer Data
demand projection and • Trade Publications
viability?
• Do we need to have
Research Begins here contingency measures?
What?
What this means…???
THANK YOU 