CS Colloquium: Route Recommendations for Taxi Drivers: Find Me the Shortest Route to a Customer!

Date and Location

May 20, 2019 - 3:30pm to 4:30pm
HFH 1132

Speaker

Sayan Ranu
Department of Computer Science and Engineering
IIT Delhi

Abstract

With the proliferation of GPS-enabled smartphones, the dynamics of the taxi service industry has changed dramatically. Instead of walking out to the street to find a taxi, we use apps in our smartphones to locate one (Ex. Uber, Ola). In this highly competitive taxi service industry, anticipating the location of future customer requests and accordingly select routes is critical toward gaining a competitive advantage. Such strategically selected routes would lead to shorter wait times for customers and reduced fuel costs for taxi drivers. In this talk, we will discuss algorithms to achieve this goal both for the traditional scenario where a customer hires the entire taxi as well as the more recent ride-sharing model. Through extensive empirical evaluation on real datasets, we will present evidence that the proposed strategies lead to up to 70% shorter waiting times for customers, 40% more customers, and 20% lower rejection rate.

This talk directly relates to some of the IGERT research modules and to the projects undertaken during the recent bootcamp. We encourage all IGERT trainees to attend.

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 a half in the role of a Research Scientist at IBM Research. He obtained his Ph.D. from the Department of Computer Science, University of California, Santa Barbara (UCSB) in March 2012. He has published several papers in tier-1 data mining venues among which he received the Best Paper Award at the International Conference on Web Information Systems Engineering (WISE) 2016, Best-of-IEEE-ICDM-2016 selection, and Most Reproducible Paper Award at SIGMOD 2018.