Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
On the Real-Time Vehicle Placement Problem
Abhinav Jauhri, Carlee Joe-Wong, John Paul Shen
Oct 31, 2017 (modified: Oct 31, 2017)NIPS 2017 Workshop MLITS Submissionreaders: everyone
Abstract:Motivated by ride-sharing platforms' efforts to reduce their riders' wait times for a vehicle, this paper introduces a novel problem of placing vehicles to fulfill real-time pickup requests in a spatially and temporally changing environment. The real-time nature of this problem makes it fundamentally different from other placement and scheduling problems, as it requires not only real-time placement decisions but also handling real-time request dynamics, which are influenced by human mobility patterns. We use a dataset of ten million ride requests from four major U.S. cities to show that the requests exhibit significant self-similarity. We then propose distributed online learning algorithms for the real-time vehicle placement problem and bound their expected performance under this observed self-similarity.
Keywords:online learning, ride-sharing, placement
Enter your feedback below and we'll get back to you as soon as possible.