Discrete choice and machine learning: Thomson and Thompson? by Professor Michel Bierlaire

This presentation was delivered as part of the Choice Modelling Centre (CMC) seminar series and Institute for Transport Studies (ITS) seminar series. Introduction by Professor Stephane Hess, ITS, University of Leeds. Abstract: Classification methods from machine learning are receiving a lot of attention in the transportation modelling community. This is motivated by the access to large databases, and to various success stories reported in this research community. Discrete choice models have been used for decades to model the behaviour of travellers, faced to various types of decisions. In this talk, we will compare the two approaches, and highlight their differences. In particular, we will identify good and less good practices in each community. Bio: Michel Bierlaire is the director of the Transport and Mobility laboratory at the Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland. Since 2009, he is the director of TraCE, the Transportation Center. Since September 2017, he is the head of the Civil Engineering Institute at EPFL. His main expertise is in the design, development and applications of models and algorithms for the design, analysis and management of transportation systems. Namely, he has been active in demand modelling (discrete choice models, estimation of origin-destination matrices), operations research (scheduling, assignment, etc.) and Dynamic Traffic Management Systems. He is the founder of hEART: the European Association for Research in Transportation. He is the Editor-in-Chief of the EURO Journal on Transportation and Logistics. He is an Associate Editor of Operations Research and an Editorial Board Editor of Transportation Research Part B.

Professor Michel Bierlaire, Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland.

6/11/2019 12:06:07 PM