Sink Proximity: A Novel Approach for Online Vehicle Dispatch in Ride-hailing

TL;DR

This paper introduces sink proximity, a network-inspired measure, to enhance real-time vehicle dispatch in ride-hailing, improving service rates during peak hours without relying on precise demand forecasts.

Contribution

The paper presents a novel measure called sink proximity and integrates it into a dispatch algorithm that considers future network states without forecast dependency.

Findings

Significantly improves request service rate during peak hours

Effectively incorporates future network states into dispatch decisions

Operates well with limited future demand information

Abstract

Ride-hailing platforms have a profound impact on urban transportation systems, and their performance largely depends on how intelligently they dispatch vehicles in real time. In this work, we develop a new approach to online vehicle dispatch that strengthens a platform's ability to serve more requests under demand uncertainty. We introduce a novel measure called sink proximity, a network-science-inspired measure that captures how demand and vehicle flows are likely to evolve across the city. By integrating this measure into a shareability-network framework, we design an online dispatch algorithm that naturally considers future network states, without depending on fragile spatiotemporal forecasts. Numerical studies demonstrate that our proposed solution significantly improves the request service rate under peak hours within a receding horizon framework with limited future information available.