2023-2024 / INFO2054-1

Marketing Analytics


30h Th

Number of credits

 Master in management (120 ECTS)5 crédits 


Siamak Khayyati

Language(s) of instruction

English language

Organisation and examination

Teaching in the second semester


Schedule online

Units courses prerequisite and corequisite

Prerequisite or corequisite units are presented within each program

Learning unit contents

Marketing analytics involves the creation and use of quantitative data to derive consumer insights or measure the performance of marketing actions. Marketing analytics enables real-time decision support as well as proactive management. It is often heralded as a critical resource necessary for effective marketing.

Part I - Data visualization:

When it comes to analyzing past data for diagnostic purposes, deciphering data from different channels, consolidating and synthesizing it, data visualization and business intelligence solutions are indispensable.

In this course, students will learn to use a data visualization software in order to build effective and powerful dashboards.

Part II - Machine Learning

When it comes to obtaining predictions or forecasts for the future, understanding the mechanisms of AI solutions and being able to adequately select a machine learning algorithm is a must. Common applications of AI in marketing are the analysis of customer loyalty, the analysis of market baskets, the identification of prospective customers,  recommendation tools, identification, calculation of conversion probabilities,...

In this course, students will learn about the basic concepts of predictive modelling and discover descriptive and predictive techniques like

  • Association analysis
  • Clustering/Automatic Segmentation
  • kNN
  • Regression (linear and logistic) and Artificial Neural Networks
  • Decision trees and Random forests
Throughout the course, emphasis will be placed on the understanding and real life application of these techniques. Students will directly put them into practice through the use of several reporting/data mining softwares.

Learning outcomes of the learning unit

Upon completion of this unit, the student will be able to:

  • manipulate complex data sets and summarize them in powerful dashboards
  • explain and understand the fundamental concepts of machine learning
  • think and propose machine learning solutions for a concrete business problem
  • anticipate the pitfalls of a machine leraning project
  • select a machine learning method adapted to the context, the problem and the dataset
  • implement machine learning methods on datasets
  • interpret and criticize the results of such methods

Prerequisite knowledge and skills

Basic computer skills.

Basic statistics (descriptive statistics, and elements of probability)

Planned learning activities and teaching methods

Emphasis will be placed on the understanding and real-life application of the analytics methods atught. To this end, all the theoretical concepts will be directly illustrated on small examples and students will practice on real-data examples. They will acquire a basic theoretical knowledge but also learn to use professional analytics tools.

The students will have to complete two group projects on a provided dataset.

A flipped classroom approach is used for some chapters:  the students have to prepare some topics before the lecture thanks to an online tutorial and/or slides. The lecture will then focus on the difficulties encountered during the preparation, as well as on the interpretation of the results.

The projects and the preparations are compulsory.  If a student has not completed all his/her assignments, he/she will not be allowed to sit the exam (failure mark).

Mode of delivery (face to face, distance learning, hybrid learning)

All lectures require the use of a computer.

Recommended or required readings

All required documents will be published on Lol@.

Exam(s) in session

Any session

- In-person

written exam ( multiple-choice questionnaire, open-ended questions )

Written work / report

Additional information:

Students are evaluated on the following elements:

  • Project 1 : Data visualization
  • Project 2 : Machine Learning
  • Exam Part 1: Understanding of the methods
  • Exam Part 2 : Practice Data visualization 
  • Exam Part 3 : Practice Machine Learning 
The final grade is computed as follows :

  • Understanding of the methods (Exam Part 1) : 2/8
  • Practice Data visualization (Project 1 + Exam Part 2) : 3/8
  • Practice Machine Learning (Project 2 + Exam Part 3) : 3/8
The projects and the preparations are compulsory.  If a student has not completed all his/her assignments (first and second sessions), he/she will obtain a failure mark and will not be allowed to sit the exam.

Work placement(s)

Organisational remarks and main changes to the course

The examinations are organized twice a year during the official sessions.  All the students sit the exam in Liège.  Due to the nature of this course, we do not accept to organize any additional exam at a different date and/or at a different location (even for students from abroad).


S. Aerts, HEC-ULg, N1  Stephanie.Aerts@uliege.be

Association of one or more MOOCs