PhD Dissertation Proposal by JI Mengyu

In many major cities around the globe, taxi-like services (both traditional taxis and ride-hailing services such as Uber or Lyft) have become more and more important in providing point-to-point transportation services. This is especially true for locations that generate large amount of demands in a spiky manner and are relatively isolated. Best examples of such locations are airports, rail stations, stadiums, and conference/exhibition centers. In my first work, I propose a highly effective passenger demand prediction system that is based on the real-time flight arrival information. We then propose an optimal control strategy based on a Markov Decision Process to model the decisions of notifying individual taxis that are at different distances away from the airport. In my second work, I focus on taxi drivers rationality, modelling taxi drivers behaviour by Cognitive Hierarchy (CH) model. My objective is to find learning by doing effects by investigating drivers levels of reasoning evolution. For my future work, my research objective is to combine demand prediction system in my first work with taxi drivers levels of reasoning, we are going to build two-way communication frame and provide guidance to taxi drivers.

JI Mengyu is a PhD Candidate in the School of Computing and Information Systems, Singapore Management University, under supervision of Professor CHENG Shih-Fen. She received her Bachelor's degree in Southern University of Science and Technology in 2017. Her research interests mainly lies on Urban Transportation Systems, which currently focuses on real-world demand prediction system as well as taxi drivers behaviour, and her research objective is to build a taxi guidance system to help drivers in improving their revenue, decreasing their queue time and so on.