Mobility Data-driven Complete Dispatch Framework for the Ride-hailing Platform

ABSTRACT Global urbanization has enabled worldwide economic growth over the past decade. Such legend yields a dramatically increasing population for major metropolises, which heavily burdens the transportation sector. The huge personal transportation demands warrant an efficient platform to support dynamic mobile services and their operation. In this work, we focus on the complete dispatch for the ride-hailing platform. We first model the uncertainty in both the supply side and demand side. Then we propose a network flow accelerated algorithm to obtain the dispatch policy when perfect information is available. Then considering the case without perfect information, we further combine network flow formulation and learning framework, and propose the data-driven network flow accelerated algorithm to improve the platform efficiency. In numerical studies, we seek to explore the value of information on the demand side and supply side using real data.