The course introduces the theoretical foundations to choice modeling and describes the steps of operational modeling.

Course Details

Language English
Duration 7 week
Effort 6 hour/week

Human behavior is complex and unpredictable. Or is it?

The focus of this course is methods for predicting the behavior using mathematical models. More specifically, we'll explore choice modeling in order to obtain disaggregate demand models.  

Focusing on the logit model, the course covers the specification of the model, the estimation of its parameters, the validation process, and its application. Exercises using the software Biogeme are also part of its makeup. The course relies on concrete case studies with real data sets, which are provided in course content.

What you will learn

  • The behavioral assumptions associated with disaggregate choice models

  • The derivation of operational models

  • The art of model specification

  • The estimation of model parameters from choice data

  • The testing of model specifications

  • Concrete applications of the estimated models


Statistics (bachelor level), linear regression


1. Introduction to behavior modeling
2. Theoretical foundations
3. Binary choice
4. Biogeme: an open-source software for estimating choice models
5. Choice with multiple alternatives
6. Testing
7. Forecasting

Course instructors

Prof. Michel Bierlaire

Michel Bierlaire holds a PhD in Mathematical Sciences from the University of Namur, Belgium. Between 1995 and 1998, he was research associate and project manager at the Intelligent Transportation Systems Program of the Massachusetts Institute of Technolog…

École polytechnique fédérale de Lausanne

Free online courses from École polytechnique fédérale de Lausanne

EPFL is the Swiss Federal Institute of Technology in Lausanne. The past decade has seen EPFL ascend to the very top of European institutions of science and technology: it is ranked #1 in E…

95 instructors