Keynote speaker

Michel Bierlaire

Michel Bierlaire is a Professor of École Polytechnique Fédérale de Lausanne (EPFL), Switzerland, where he is also the Director of the Transport and Mobility Laboratory. He has been active in demand modeling, discrete choice, operations research, and dynamic traffic management systems. His research interests include the design, development, and applications of models and algorithms for the design, analysis, and management of transportation systems.  He was the founding Editor-in-Chief of the EURO Journal on Transportation and Logistics from 2011 to 2019. He has been an Associate Editor of Operations Research since 2012.  He is the founder of hEART, the European Association for Research in Transportation.

Predicting Human Behavior with Optimization

Choice behavior lies at the core of numerous real-world applications, notably in transportation planning and marketing. Operational choice models, grounded in random utility theory, postulate that individuals select the alternative offering the highest utility. While effective in many contexts, these models rely on the explicit enumeration of all available alternatives—a requirement that becomes impractical or infeasible when the choice set is large or complex. In this talk, we present an approach that leverages combinatorial optimization techniques to address this limitation. We illustrate the methodology with a case study in travel demand modeling, where the integration of optimization enables the analysis of rich and realistic choice sets without exhaustive enumeration.