Discrete Choice Analysis


Predicting Individual Behavior and Market Demand, Remote course taught by Moshe Ben-Akiva, 12-16 Jun 2023


Author: Katie Rosa

Dear Colleagues,

We would like to invite you to a one-week MIT course taught remotely from June 12-16, 2023:

Discrete Choice Analysis: Predicting Individual Behavior and Market Demand

Discrete choice models are used in many fields such as economics, engineering, environmental management, marketing, urban planning, and transportation. The course is designed for modelers who wish to acquire in-depth knowledge of the latest developments.  It is intended for both academics and professionals.

The course covers: alternative models including Logit, Probit, Nested Logit, Multivariate Extreme Value, discrete and continuous Logit Mixtures and Hybrid Choice Models; and alternative estimation methods including simulated maximum likelihood, Hierarchical Bayes, instrumental variable methods and random effects in panel data.  Recent additions to the course include “Foundations of Stated Preference Elicitation: Consumer Behavior and Choice-based Conjoint Analysis” by Moshe Ben-Akiva, Daniel McFadden and Kenneth Train, estimation of flexible model specifications using machine learning methods and online applications for optimization and personalization.  Each day of this course consists of lectures followed by a computer lab to apply the lectured methods with open source software and data sets. Initial lectures and lab session review required fundamental concepts.

One full-tuition scholarship will be awarded to an outstanding doctoral student with an application deadline of April 30, 2023. Partial scholarships (50%) are available for junior faculty, postdocs, and doctoral students.

Additional information is available here. We appreciate your help in making people aware of this unique opportunity to study this summer at MIT.

Thanks, Moshe

Moshe Ben-Akiva
Massachusetts Institute of Technology
Edmund K. Turner Professor of Civil and Environmental Engineering
Director, Intelligent Transportation Systems Lab