Exploring the Tradeoff Between System Profit and Income Equality Among Ride-hailing Drivers

Document Type

Article

Publication Date

1-1-2024

Abstract

This paper examines the income inequality among rideshare drivers resulting from discriminatory cancellations by riders, considering the impact of demographic factors such as gender, age, and race. We investigate the tradeoff between income inequality, referred to as the fairness objective, and system efficiency, known as the profit objective. To address this issue, we propose an online bipartite-matching model that captures the sequential arrival of riders according to a known distribution. The model incorporates the notion of acceptance rates between driver-rider types, which are defined based on demographic characteristics. Specifically, we analyze the probabilities of riders accepting or canceling their assigned drivers, reflecting the level of acceptance between different rider and driver types. We construct a bi-objective linear program as a valid benchmark and propose two LP-based parameterized online algorithms. Rigorous analysis of online competitive ratios is conducted to illustrate the flexibility and efficiency of our algorithms in achieving a balance between fairness and profit. Furthermore, we present experimental results based on real-world and synthetic datasets, validating the theoretical predictions put forth in our study.

Identifier

85185200881 (Scopus)

Publication Title

Journal of Artificial Intelligence Research

External Full Text Location

https://doi.org/10.1613/jair.1.15170

ISSN

10769757

First Page

569

Last Page

597

Volume

79

Grant

IIS-1948157

Fund Ref

Fundamental Research Funds for the Central Universities

This document is currently not available here.

Share

COinS