On the Dynamism of User Rejections in Mobility-on-Demand Systems

TL;DR

This paper explores how dynamic state optimization in ride-hailing systems can improve user experience by reducing waiting times and computational costs through early rejections, leading to more efficient and responsive mobility-on-demand services.

Contribution

It introduces a method for early user rejection in MoD systems using dynamic optimization, enhancing responsiveness and computational efficiency.

Findings

Early rejections reduce user waiting time.

Faster re-optimization cycles improve system responsiveness.

Computational resources are conserved through problem dimension reduction.

Abstract

Mobility-on-demand (MoD) systems, especially ride-hailing systems, have seen tremendous growth in recent years. These systems provide user-centric mobility services, whose users expect a high level of convenience. Waiting for a response after an app request and eventually learning after a long period of time that no vehicle is available is hardly acceptable. This study investigates the use-case where users should be served within a certain maximum waiting time. Under certain assumptions, which are reasonable for an attractive MoD business model, it can be shown that an operator using dynamic state optimization can communicate a rejection to users after the first iteration, thereby eliminating unnecessary waiting time before these users would leave the system. Furthermore, early operator rejections reduce the dimension of subsequent customer-vehicle assignment problems, thereby saving computational resources and solving the problems faster. In turn, this allows shorter re-optimization cycles and once again faster responses, i.e. a better user experience.