In the current world, once a taxi drops a customer in his/her destination, no further intelligence is provided to the taxi driver to reduce the wait-time for the next customer request. Either the taxi remains stationary or it drives towards a “hot-spot” that typically has high density of customers. Our goal is to develop a data-backed algorithm that recommends routes to drivers during their idle time such that the distance between them and the next anticipated customer request is minimized. Minimizing the distance to the next anticipated customer leads to more productivity for the taxi driver and less waiting time for the customer. To anticipate when and where future customer requests are likely to come from and accordingly recommend routes, we develop a route recommendation engine called MDM: Minimizing Distance through Monte Carlo Tree Search. In contrast to existing techniques, MDM employs a continuous learning platform where the underlying model to predict future customer requests is dynamically updated. Extensive experiments on real taxi data from New York and San Francisco reveal that MDM is up to 70% better than the state of the art and robust to anomalous events such as concerts, sporting events, etc.
Sayan Ranu is an assistant professor in the department of Computer Science and Engineering at IIT Delhi. His research interests include spatio-temporal data analytics, graph indexing and mining, and bioinformatics. Prior to joining IIT Delhi, he spent close to three years as an Assistant Professor at IIT Madras and a year and half in the role of a Research Scientist at IBM Research. He obtained his PhD from the Department of Computer Science, University of California, Santa Barbara (UCSB) in March 2012. He has published more than 28 papers including in premier data-mining conferences such as SIGMOD, VLDB, KDD, ICDM, and WWW. He received the Best Paper Award at the International Conference on Web Information Systems Engineering (WISE), 2016 and Most Reproducible Paper Award in SIGMOD 2018. Sayan regularly serves in the program committees and review panels of prestigious conferences and journals including KDD, SDM, WWW, ICDM, TKDE, and VLDB Journal.