28 JUN 2022 (TUE) | 11:30-12:30 HKT

Ride-Sourcing Systems & Multiple-Objective Online Ride Matching

DOWNLOAD LECTURE POSTER

SPEAKER:

Dr Hai WANG Singapore Management University, Singapore

DATE & TIME:

June 28 (Tuesday) 11:30-12:30 HKT

VENUE:

Room 632, 6/F, Haking Wong Building, The University of Hong Kong

ZOOM:

https://hku.zoom.us/j/97369816828 (Meeting ID: 973 6981 6828)

ABSTRACT:

We propose a general framework to study the on-demand shared ride-sourcing transportation systems and summarize the relevant research problems in four areas, namely, demand, supply, platform operation, and system problems. We then focus on the online matching problem, in which the platforms match passengers and drivers in real-time without observing future information, considering multiple objectives such as pick-up time, platform revenue, and service quality. Given stationary and non-stationary decision scenarios, we develop efficient online matching policies that adaptively balances the trade-offs between multiple objectives in a dynamic setting and provide theoretical performance guarantees for the policy. Through numerical experiments and industrial testing using real data from a ride-sourcing platform, we demonstrate that our approach can arrive at a delicate balance among multiple objectives and bring value to all the stakeholders in the ride-sourcing ecosystem.

ABOUT THE SPEAKER:

Dr. Wang is an Associate Professor in the School of Computing and Information Systems at Singapore Management University and a visiting faculty at the Heinz College of Information Systems and Public Policy at Carnegie Mellon University. He received B.S. from Tsinghua University and Ph.D. in Operations Research from MIT. His research focuses on methodologies of analytics and optimization, data-driven decision-making models, machine learning algorithms, and their applications in smart cities, transportation and logistics systems. He has published in leading journals such as Transportation Science, American Economic Review P&P, M&SOM, and Transportation Research Part B/C. He has long term collaborations with leading companies such as DiDi, Meituan, Tencent, and Upwork. He serves as Associate Editor for Transportation Science, Special Issue Guest Editor for Transportation Research Part B, Part C, and Service Science, and Editorial Board Member for Transportation Research Part E. Dr. Wang was selected as Chan Wu & Yunying Rising Star Fellow in transportation and mobility, received Lee Kong Chian Research Excellence Award, was nominated for MIT’s top graduate teaching award, and won the Excellent Teaching award for junior faculty at SMU. During his Ph.D. studies at MIT, he also served as the co-President of the MIT Chinese Students & Scholars Association and as Chair of the MIT-China Innovation and Entrepreneurship Forum.

CO-ORGANIZERS:

Department of Civil Engineering & Institute of Transport Studies, The University of Hong Kong

08 JUN 2022 (WED) | 13:00-14:00 HKT

A Method to Match Users Across Transportation Modes Based on Repeated Transfer Behaviors

REGISTRATION: https://bit.ly/3uyVv5d (Deadline: 07 June 2022, 12:00)

DOWNLOAD LECTURE POSTER

This seminar will be via ZOOM only.

SPEAKER:

Dr Hongtai Yang Associate Professor, Southwest Jiaotong University

DATE & TIME:

June 08 (Wednesday) 13:00-14:00 HKT

ABSTRACT:

For the purpose of privacy protection, trip trajectory data containing rich personal travel information needs to be anonymized before being shared and analyzed. This practice makes it difficult for researchers to identify the same individuals in different datasets, which hinders the construction of complete trip chains and the exploration of important travel patterns. Therefore, this paper develops a method to match users of different transportation modes based on the following idea. If a user makes a transfer, the ending point of the previous trip will be around the same time (a little earlier) and same location as the starting point of the next trip. When this pattern happens for two user accounts repeatedly, we can infer that the two users are actually the same person. This method is demonstrated using the metro and bus data of Chengdu city from January to March 2021. When setting the minimum transfer times as three, the precision and recall of user matching is 56.50% and 26.45% for the one-month data, 61.76% and 38.60% for the two-month data, and 65.36% and 50.49% for the three-month data. Sensitivity analysis is performed to study the effect of parameters on the user matching result.

ABOUT THE SPEAKER:

Hongtai Yang is an associate professor of Southwest Jiaotong University, located in Chengdu, China. He obtained his PhD in civil engineering with emphasis on transportation engineering and MS in statistics from The University of Tennessee at Knoxville. His research interests include urban big data analytics and multimodal transportation demand management. He has served as PI for research projects from various funding sources such as National Science Foundation of China and China Postdoctoral Science Foundation. He serves as an academic editor of Journal of Advanced Transportation and an editorial board member of China Safety Science Journal. He has published more than 40 papers on journals such as Transportation Research Part A/D/F and IEEE Transaction on Intelligent Transportation Systems, and five of them have been selected as ESI highly cited papers.

ORGANIZER:

Institute of Transport Studies, The University of Hong Kong