Learning to Assign: Towards Fair Task Assignment in Large-Scale Ride Hailing
Authors:
Open Access
- 14 August 2021
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 3549-3557
Abstract
Ride hailing is a widespread shared mobility application where the central issue is to assign taxi requests to drivers with various objectives. Despite extensive research on task assignment in ride hailing, the fairness of earnings among drivers is largely neglected. Pioneer studies on fair task assignment in ride hailing are ineffective and inefficient due to their myopic optimization perspective and time-consuming assignment techniques. In this work, we propose LAF, an effective and efficient task assignment scheme that optimizes both utility and fairness. We adopt reinforcement learning to make assignments in a holistic manner and propose a set of acceleration techniques to enable fast fair assignment on large-scale data. Experiments show that LAF outperforms the state-of-the-arts by up to 86.7%, 29.1%, 797% on fairness, utility and efficiency, respectively.Keywords
This publication has 14 references indexed in Scilit:
- Stable Matching for Dynamic Ride-Sharing SystemsTransportation Science, 2018
- Large-Scale Order Dispatch in On-Demand Ride-Hailing Platforms2018
- A Taxi Order Dispatch Model based On Combinatorial Optimization2017
- The Simpler The Better2017
- Online minimum matching in real-time spatial dataProceedings of the VLDB Endowment, 2016
- Budget-Optimal Task Allocation for Reliable Crowdsourcing SystemsOperations Research, 2014
- Online bottleneck matchingJournal of Combinatorial Optimization, 2012
- Fair online load balancing2006
- Theoretical Improvements in Algorithmic Efficiency for Network Flow ProblemsJournal of the ACM, 1972
- Methods of Measuring the Concentration of WealthPublications of the American Statistical Association, 1905