This talk proposed a general framework to study the on-demand shared ride- sourcing transportation systems and summarized the relevant research problems in four areas, namely, demand, supply, platform operation, and system problems. The problem of online matching in the ride-sourcing systems was the main focus of this seminar. The platforms matched passengers and drivers in real time without observing future information, considering multiple objectives such as pick-up time, platform revenue, and service quality. Then, an efficient online matching policy was developed that adaptively balanced the trade-offs between multiple objectives in a dynamic setting and provided theoretical performance guarantees for the policy. It was proven that the proposed adaptive matching policy can achieve the solution that minimizes the Euclidean distance to any pre-determined multi-objective target. Through numerical experiments and industrial testing using real data from a ride-sourcing platform, the approach was demonstrated to be able to arrive at a delicate balance among multiple objectives and bring value to all the stakeholders in the ride- sourcing ecosystem.

Dr. Wang is currently a Visiting Assistant Professor at the Heinz College of Information Systems and Public Policy at Carnegie Mellon University. He received a Bachelor’s degree from Tsinghua University, dual Master’s degrees in operations research and transportation from MIT, and a doctoral degree in operations research from MIT. Dr. Wang is also an Assistant Professor in the School of Information Systems at Singapore Management University. His research has focused on methodologies of analytics and optimization, data-driven decision-making models, and machine learning algorithms, and their applications in the general context of smart cities and urban systems, including transportation, logistics, and healthcare systems.