Uncategorized
Seminar by Zhenliang Ma
We had the pleasure of hosting Professor Zhenliang Ma, Associate Professor in Transportation Systems at KTH and Faculty at KTH Digital Futures, for an insightful seminar on:
Title: Causal AI for Behavior Learning from Trajectory Data: Case Studies in Public Transportation
Professor Ma’s talk delved into the power of Causal AI and Inverse Reinforcement Learning to understand human mobility and behavioral shifts in public transportation. Through real-world case studies, such as the Hong Kong Mass Transit Railway’s pre-peak fare discount program, he showcased how mobile and smart card data can model behavior change and improve transit systems. Key insights included:
- Data-driven causal inference for understanding mobility shifts under incentive programs
- Inverse reinforcement learning to predict individual behavior changes
Below you can find the abstract and more information about Ma’s research interests.
Abstract: Understanding and modelling human mobility are fundamental for applications from planning to operations and management in cities. Mobile sensing has enabled us to collect a large amount of mobility data from human decision-makers, for example, GPS trajectories from mobile phones and passenger trip data of taking buses and trains from smart card data. The presentation will demonstrate the applicability and value of the data with examples of recent developments, including a) Data-driven causal inference of behavior changes under incentive interventions, and 2) Inverse reinforcement learning for individual behavior change prediction. The methods are validated using smart card data for a real-world case study on a pre-peak fare discount incentive program in the Hong Kong Mass Transit Railway system. The methodology and empirical findings as well as the future envisions of AI for behavior learning will be discussed.
Short Bio: Zhenliang Ma is Associate Professor in Transportation Systems at Transport Planning Division at KTH, and Faculty Member of KTH Digital Futures. His research focuses on data science based modeling, simulation, optimization, and control of mobility-related systems, which are: intelligent transport systems and multimodal mobility systems. He is an Associate Editor of IEEE Transactions on Intelligent Transportation Systems, Associate Editor of Journal of Public Transportation, and TRB Committee Member (AP090-Transit Data and AEP060-Travel Demand Management).
