#183: NextGen Disaggregate Travel Demand Models: From Synthetic Populations to Activity-based Models with Michel Bierlaire
For decades, transportation planning has relied on models that simplify an extraordinarily complex question:
How will millions of different people respond when we change the transportation system?
A new generation of travel demand modeling is pushing toward much greater behavioral detail.
Instead of representing populations primarily through aggregate groups and snapshots, researchers are developing complex synthetic populations that can evolve over time, incorporate household and social relationships, and feed into increasingly sophisticated activity-based models.
At the same time, advances in discrete choice modeling and computation are making it possible to model decisions involving enormous numbers of alternatives—bringing travel demand models closer to the complexity of the choices people actually face.
What does this mean for the future of transportation modeling?
In this episode, I will speak with Michel Bierlaire, Professor at EPFL about this new generation of disaggregate travel demand models.
Professor Bierlaire recently received an ERC Advanced Grant for Combinatorial Optimization for Behavioral Response Analysis (COBRA). His research spans discrete choice, travel demand analysis, activity-based modeling, synthetic populations, optimization, and transportation systems analysis.
We will explore:
Beyond the population snapshot: Can synthetic people acquire life histories, households, social relationships, and changing behavior?
The explosion of choice: How can models represent decisions when travelers face thousands—or millions—of possible alternatives?
From trips to lives: What does activity-based modeling allow us to understand that conventional travel demand models cannot?
AI and behavioral modeling: Where can machine learning and generative AI strengthen behavioral models—and where do they risk sacrificing interpretability and behavioral theory?
From research to practice: If these models are so powerful, why aren't they already standard tools in transportation planning?
Are we building more sophisticated travel demand models or changing how transportation understands and predicts human behavior?