Haochen Tang, Michael Kerber, Qixing Huang, and Leonidas Guibas. Locating Lucrative Passengers for Taxicab Drivers. In Proceedings of the 21th SIGSPATIAL International Conference on Advances in Geographic Information Systems, GIS ’13, 2013.

Abstract:

In an urban setting such as the city of Beijing, after a taxi driver drops the previous passenger, he/she needs to decide where to drive to find the next - preferably lucrative - passenger. Different drivers follow different strategies that are mostly based on personal experiences. In this work, we analyze large amount of GPS location data of taxicabs to compute a high-level strategy for taxi drivers. Formally, we model the problem of finding a passenger as a Markov Decision Process (MDP) so that the sequential effect of the taxi driver decision is well dealt with. The parameters of the MDP are obtained from the GPS data and we compute an optimal policy using dynamic programming. We demonstrate that taxi drivers that follow our proposed strategy indeed generate more profit than average.

Bibtex: 

@inproceedings{tkhg-llptd-13,
 author = {Haochen Tang and Michael Kerber and Qixing Huang and Leonidas Guibas},
 title = {Locating Lucrative Passengers for Taxicab Drivers},
 booktitle = {Proceedings of the 21th SIGSPATIAL International Conference on Advances in Geographic Information Systems},
 series = {GIS '13},
 year = {2013},
 location = {Orlando, Florida}
}