Fleet size planning in crowdsourced delivery: Balancing service level and driver utilization

Abstract

This paper addresses the fleet size planning problem for crowdsourced delivery platforms, focusing on optimizing the number of crowdsourced drivers to balance the platform’s service level and driver utilization. This is motivated by recent regulatory measures that limit the number of vehicle licenses a platform can hold, which caps fleet size as a means to enhance driver working conditions and mitigate congestion and emissions caused by an excessive number of idle vehicles on the road. We propose a two-stage optimization model where the first stage involves tactical decisions for determining fleet sizes, while the second stage captures the operational dynamics of the platform by a Markov decision process (MDP) in which uncertain crowd driver arrival in the MDP depends on fleet size decisions in the first stage, introducing decision-dependent uncertainty. To efficiently solve the model, we employ a value function approximation (VFA) algorithm that iteratively determines fleet sizes using Boltzmann exploration then approximates the second-stage MDP using a rolling-horizon parametric cost function approximation. Extensive computational experiments confirm the effectiveness of the VFA algorithm, demonstrating its ability to meet both service level and driver utilization targets under various conditions. The results show that a platform can achieve high driver utilization and meet its service level target while only marginally reducing its profit, especially when driver behavior is more predictable and fleet sizes are temporally adjusted.