讲座：The Logic of Matching in Ride Sharing Markets: Revenues, Service Ratings or Pick-Up Times?
题 目：The Logic of Matching in Ride Sharing Markets: Revenues, Service Ratings or Pick-Up Times?
演讲人：Hai Wang， Assistant Professor, Singapore Management University
We study a class of multi-period multi-objective online optimization problems, where a decision maker takes actions over time in an online fashion without being informed of future scenarios. To balance the trade-offs between different objectives, we develop an efficient online policy to derive the “compromise solution”, which minimizes the “p-distance” from the attained KPIs to the utopia target. We apply the online policy in ride sharing market settings, and provide an online matching policy that simultaneously incorporates driver service scores, pick-up distances and passenger revenues. Extensive numerical simulations based on real ride sharing records reveal the benefits of the policy: (1) drivers with higher service scores are dispatched with more orders; (2) passengers are more likely to be matched to drivers with higher service scores; (3) the platform obtains a higher revenue and better long-term brand reputation. Compared to legacy policies currently in use, such as the weighted average policy or the “closest distance” policy, we observe that all parties in the ride-sharing eco-system, from drivers, passengers, to the platform, are better off under our proposed online matching policy.