Marketing Analytics in the Digital Era

Group	Teacher	Department	Language
	Skander Esseghaier	Marketing	ENG

COURSE CONTRIBUTION TO PROGRAM

In the core Marketing Management course, you learned about the importance of Market Segmentation, Targeting and Positioning in formulating marketing strategies. But as a marketing analyst (whether you are working in management strategy consulting or in brand management), you would be faced with the key question: How does one implement these strategies in practice?

The industrial Internet is increasingly allowing firms to measure consumer data (usage data, perceptions data and preference data) as part of regular business, without a study. Large amounts of data are collected, stored and organized. Such "Big Data" can be today retrieved easily, visualized in a simple manner, and made available to marketing strategists.

"Marketing Analytics" will equip you with practical tools to leverage consumer and market data to implement marketing strategies and to aid you in making strategic decisions.

The class will combine lectures on "what" these techniques are and "when" to apply them with hands on Minitab sessions on "how" to perform the analysis and interpret the output to take decisions.

The course will have a heavy "hands-on" flavor, where we will analyze dataset using the "Minitab" statistical analysis program.

A laptop is needed for this class (in-class and outside of class). You should bring it to all class sessions. In the first class meeting, we will make sure that everybody get access to the Minitab software via the MyLab portal. Make sure you bring your laptop to the first class session on Wednesday 20 February 2019.

You are expected to be fully engaged in the entire learning process.
- No cell phones are allowed in the classroom. You will be asked to leave the classroom should you use your cellphone during class time.
- Detailed note-taking during class is counterproductive to your own learning. I will share with you very detailed notes that exhaustively cover the content of the lectures in this course during class. This course will have a heavy "hands-on" flavor where the focus would be on "how" to perform the analysis and interpret the output to take decisions. Instead, it is a good idea to consolidate what you have learned after the class.

CONTENT

1. Wednesday 20 February 2019: Morning Session COURSE INTRODUCTION We will start the course by highlighting how today's dramatic increase in the availability of data to support strategic decision making is a a double edge sword, and why you would need to develop what I call a "working knowledge of market data analytics." This is because on the one hand, the fact that "data" is increasingly available to support strategic decision making is an absolutely amazing advance. But on the other hand, it is going to challenge you as a marketing strategist because it is now up to you understand what the measurement data tells you about your consumers and your markets. COURSE ORGANIZATION We will also discuss some organizational aspects of the course. You will be extensively using the MINITAB statistical software in the classroom, starting from day 1. We will therefore make sure that everyone has access to the MINITAB software via the MyLab portal in this first class meeting. Please make sure your bring your laptop to the classroom TODAY and at every class meeting. QUIZ ON COURSE PREREQUISITE CONTENT ¿BASIC STATISTICS¿ The class will start with a quiz on basic statistics. This is the content you are required to be familiar with before the start of the course (prerequisite).
2. Wednesday 20 February 2019: Afternoon Session LINKING CAUSES AND EFFECTS BETWEEN RESOURCES ALLOCATIONS AND DESIRED MARKET OUTCOMES The goal of this session is to introduce you to thinking with data. We will examine the difference between association and dependence and between association and causation and why they matter for data driven decision making. We will highlight the notion of confounding factors and how critical it is to eliminate alternatives explanations when we are trying to use data to link causes and effects between the resources allocations we make and the desired market outcomes we seek. We will review linear regression analysis and see how we can use it to help us in that respect. We will use a hand-on approach were you would be given a managerial problem and actual data to analyze and provide data driven answers,
3. Wednesday 27 February 2019: Morning Session ADVANCED TOPICS IN REGRESSION ANALYTICS In this session, we will examine how we can leverage the power of regression analytics to generate business insights from a wide range of data, We will explore the issues of multicollinearity and interaction effects. We will also explore when and how we need to transform our data in order to successfully apply regression analytics on them.
4. Wednesday 27 February 2019: Afternoon Session REVISITING THE CARDIO MACHINES EXAMPLE In this one-hour session, we will revisit the cardio machines example (that we discussed in the opening session of the course) with the use of actual consumer usage data and regression analytics.
5. Wednesday 6 March 2019: Morning Session DEVELOPING A CUSTOMER SELECTION STRATEGY In this session, we will examine the use of logistic analytics in helping you develop a customer selection strategy. Though a hands on example, you will learn how a logistic regression can help you identify different categories of customers on the basis of consumer data (e.g., usage data; demographic data) Reading: - Notes on Developing a Customer Selection Strategy using Logistic Analysis
6. Wednesday 6 March 2019: Afternoon Session DEVELOPING A CUSTOMER SELECTION STRATEGY (Continued) In this session, we will complete our discussion on the use of logistic analytics in helping you develop a customer selection strategy. Reading: - Notes on Developing a Customer Selection Strategy using Logistic Analysis REVIEW OF INDIVIDUAL HOMEWORK #1 (Regression Analytics)
7. Wednesday 13 March 2019: Morning Session UNDERSTANDING CLUSTER ANALYTICS In this session we will learn the basic idea of cluster analytics through a simple example, the segmentation of cities based on their geographical location (longitude and latitude): 1- how the clustering algorithm works; 2- how it helps to assess the number of distinct groups that exist in the markets; and 3- how to check the validity of the segmentation scheme obtained using cluster analytics. Reading: - Notes on Segmentation using Cluster Analysis
8. Wednesday 13 March 2019: Afternoon Session CUSTOMER SEGMENTATION & SEGMENT PROFILING In this session we will learn how to segment a market and profile its segments using cluster analytics. We will develop a segmentation of shoppers for a target market based on their attitude towards shopping (attitudinal segmentation). We will also see how cluster analytics help us interpret and profile the different segments. REVIEW OF INDIVIDUAL HOMEWORK #2 (Logistic Analytics)
9. Wednesday 20 March 2019: Morning Session INTRODUCTION TO CONJOINT ANALYTICS We will then introduce one of the most important analytics tool in today's business environment, namely conjoint analytics. We will introduce the key idea of conjoint analysis through a simple example. This would enable us to build a solid understanding of its key idea and the intuition behind it. KEY ASPECTS OF A CONJOINT STUDY (1) design of a conjoint study; (2) analysis of a conjoint study. Readings: - Notes on Conjoint Analysis
10. Wednesday 20 March 2019: Afternoon Session BENFIT SEGMENTATION AND MARKET SHARE SIMULATION In this session, we will discuss two major applications of conjoint analytics: (1) benefit-based segmentation, and (2) market share simulation. (If time allows, we will conclude our discussion of conjoint analytics by examining its use in optimal product design.) Readings: - Fedewa, Narayan and Vardhan (Mc Kinsey 2008), Designing the Value In - Bryan Orme (Sawtooth Software 2001), Assessing the monetary value of attributes using conjoint analysis
11. Friday 22 March 2019 - REVIEW SESSION (10:30-12:00) REVIEW OF GROUP HOMEWORK (Cluster Analytics) COURSE WRAP-UP AND FINAL EXAM PREPARATION GUIDELINES
12. Wednesday 3 April 2019 - FINAL EXAM (14:00 - 17:00) In class 3-hour closed books exam

1. Wednesday 20 February 2019: Morning Session

COURSE INTRODUCTION
We will start the course by highlighting how today's dramatic increase in the availability of data to support strategic decision making is a a double edge sword, and why you would need to develop what I call a "working knowledge of market data analytics." This is because on the one hand, the fact that "data" is increasingly available to support strategic decision making is an absolutely amazing advance. But on the other hand, it is going to challenge you as a marketing strategist because it is now up to you understand what the measurement data tells you about your consumers and your markets.

COURSE ORGANIZATION
We will also discuss some organizational aspects of the course. You will be extensively using the MINITAB statistical software in the classroom, starting from day 1. We will therefore make sure that everyone has access to the MINITAB software via the MyLab portal in this first class meeting. Please make sure your bring your laptop to the classroom TODAY and at every class meeting.

QUIZ ON COURSE PREREQUISITE CONTENT ¿BASIC STATISTICS¿
The class will start with a quiz on basic statistics. This is the content you are required to be familiar with before the start of the course (prerequisite).

2. Wednesday 20 February 2019: Afternoon Session

LINKING CAUSES AND EFFECTS BETWEEN RESOURCES ALLOCATIONS AND DESIRED MARKET OUTCOMES
The goal of this session is to introduce you to thinking with data. We will examine the difference between association and dependence and between association and causation and why they matter for data driven decision making. We will highlight the notion of confounding factors and how critical it is to eliminate alternatives explanations when we are trying to use data to link causes and effects between the resources allocations we make and the desired market outcomes we seek. We will review linear regression analysis and see how we can use it to help us in that respect. We will use a hand-on approach were you would be given a managerial problem and actual data to analyze and provide data driven answers,

3. Wednesday 27 February 2019: Morning Session

ADVANCED TOPICS IN REGRESSION ANALYTICS
In this session, we will examine how we can leverage the power of regression analytics to generate business insights from a wide range of data, We will explore the issues of multicollinearity and interaction effects. We will also explore when and how we need to transform our data in order to successfully apply regression analytics on them.

4. Wednesday 27 February 2019: Afternoon Session

REVISITING THE CARDIO MACHINES EXAMPLE
In this one-hour session, we will revisit the cardio machines example (that we discussed in the opening session of the course) with the use of actual consumer usage data and regression analytics.

5. Wednesday 6 March 2019: Morning Session

DEVELOPING A CUSTOMER SELECTION STRATEGY
In this session, we will examine the use of logistic analytics in helping you develop a customer selection strategy. Though a hands on example, you will learn how a logistic regression can help you identify different categories of customers on the basis of consumer data (e.g., usage data; demographic data)

Reading:
- Notes on Developing a Customer Selection Strategy using Logistic Analysis

6. Wednesday 6 March 2019: Afternoon Session

DEVELOPING A CUSTOMER SELECTION STRATEGY (Continued)
In this session, we will complete our discussion on the use of logistic analytics in helping you develop a customer selection strategy.

Reading:
- Notes on Developing a Customer Selection Strategy using Logistic Analysis

REVIEW OF INDIVIDUAL HOMEWORK #1 (Regression Analytics)

7. Wednesday 13 March 2019: Morning Session

UNDERSTANDING CLUSTER ANALYTICS
In this session we will learn the basic idea of cluster analytics through a simple example, the segmentation of cities based on their geographical location (longitude and latitude):
1- how the clustering algorithm works;
2- how it helps to assess the number of distinct groups that exist in the markets; and
3- how to check the validity of the segmentation scheme obtained using cluster analytics.

Reading:
- Notes on Segmentation using Cluster Analysis

8. Wednesday 13 March 2019: Afternoon Session

CUSTOMER SEGMENTATION & SEGMENT PROFILING
In this session we will learn how to segment a market and profile its segments using cluster analytics. We will develop a segmentation of shoppers for a target market based on their attitude towards shopping (attitudinal segmentation). We will also see how cluster analytics help us interpret and profile the different segments.

REVIEW OF INDIVIDUAL HOMEWORK #2 (Logistic Analytics)

9. Wednesday 20 March 2019: Morning Session

INTRODUCTION TO CONJOINT ANALYTICS
We will then introduce one of the most important analytics tool in today's business environment, namely conjoint analytics. We will introduce the key idea of conjoint analysis through a simple example. This would enable us to build a solid understanding of its key idea and the intuition behind it.

KEY ASPECTS OF A CONJOINT STUDY
(1) design of a conjoint study;
(2) analysis of a conjoint study.

Readings:
- Notes on Conjoint Analysis

10. Wednesday 20 March 2019: Afternoon Session

BENFIT SEGMENTATION AND MARKET SHARE SIMULATION
In this session, we will discuss two major applications of conjoint analytics: (1) benefit-based segmentation, and (2) market share simulation. (If time allows, we will conclude our discussion of conjoint analytics by examining its use in optimal product design.)

Readings:
- Fedewa, Narayan and Vardhan (Mc Kinsey 2008), Designing the Value In
- Bryan Orme (Sawtooth Software 2001), Assessing the monetary value of attributes using conjoint analysis

11. Friday 22 March 2019 - REVIEW SESSION (10:30-12:00)

REVIEW OF GROUP HOMEWORK (Cluster Analytics)

COURSE WRAP-UP AND FINAL EXAM PREPARATION GUIDELINES

12. Wednesday 3 April 2019 - FINAL EXAM (14:00 - 17:00)

In class 3-hour closed books exam

Methodology

Description	%
Quizz on Basic Statistics (in our first class meeting)	10
Individual Homework Assignment 1	15
Individual Homework Assignment 2	15
Group Homework Assignment 3	15
Class attendance and participation	20
In-Class Final Exam	25

Assessment criteria

Your final grade will be based on:
- attendance and participation in the course (20%);
- in-class quiz (10%); it will take place on the first week of classes and will test your knowledge of basic statistics (a prerequisite for this course);
- individual homework assignments (30%): there are two (2) individual homework assignment, each carrying a weight of 15%;
- one group homework assignment (15% );
- in-class final exam (25%)

Note that you need a score of 50% or greater in both the final exam and the overall course grade in order to pass this course.

Assignments must be turned in on the due dates and times specified in the syllabus; these are indicated below:
- Individual Homework #1: Submit by 8 AM on Tuesday 26 February 2019
- Individual Homework #2: Submit by 8 AM on Tuesday 5 March 2019
- Group Homework #3: Submit by 8 AM on Tuesday 12 March 2019

Assignments are to be written in a word document and then submitted in one SINGLE DOCUMENT in PDF FORMAT ONLY, and EXCLUSIVELY through MOODLE; this means:
- No excel file (if you need to share an excel spreadsheet, copy it into the appendix of your document).
- Do not submit a ppt file; do not submit a ppt file that has been converted to a pdf format;
- No word document: convert your document to a PDF file.
- No zip file with multiple documents in it.

CLASS ATTENDANCE
Attendance in every session is expected and recorded by means of an attendance sheet. It is your responsibility to comply with this measure. In addition, please remember to sign the attendance sheets next to your name and using only the signature that is on record with the MSc Programme Office. No initials, written names or other symbols are accepted as a substitute. Students who arrive 10 minutes or more after the scheduled start of class will not be allowed to enter the lecture theater unless they sought prior permission.

Class attendance is compulsory and will be considered in your final grades; punctuality is a must. Please bear in mind that there is a minimum class attendance required by the MSc Programme Direction to be able to pass this course; please check the Programme Regulations (Section 5 - Academic Integrity) to follow this requirement

CLASS PARTICIPATION
The individual participation will be assessed based on class attendance, level of participation and quality of contribution.

Basic expectations for class participation:
1- Miss no more than one class
2- Never use your cellphone in class
3- Do not sit idle during the practical sessions:
- if you are unsure about what to do or how to go about doing it, actively seek help from me or from your neighbors and classmates
- if you are done, actively seek to help some of your class mates that are behind

Students who meet these basic expectations on every session will obtain 16 participation points out of 20.

Students who exceed these expectations would have a participation grade between 17 and 20; while students who do not meet these expectations would have a participation grade no greater than 15.

INDIVIDUAL HOMEWORK ASSIGNMENTS
Individual homework assignments are given to help you gain deeper understanding of the materials covered in class. You will also gain confidence in implementing the analysis techniques on a computer.

Each student must do the analysis on their own and submit independent work to be graded. It is not acceptable to do the assignments jointly and then submit the output of the group as individual assignments. There is not one single way to do the assignments. Assignments that are similar, or that make similar mistakes would be singled out.

Type:	OP	Curs:	1	Period:	S semester
ECTS Credits:	3 ECTS

Marketing Analytics in the Digital Era (CK25318)

General information

Type:

Curs:

Period:

ECTS Credits:

Teaching Staff:

Prerequisites

Previous Knowledge

Workload distribution