Huang, Hsin-Kai (The University of Tokyo), Oyama, Yuki (The University of Tokyo), Okazaki, Ryota (Kozo Keikaku Engineering Inc.)

Balancing Efficiency and Service: A Marginal Cost Approximation Approach to Multi-Period Vehicle Routing in E-Commerce Logistics

Scheduled for presentation during the Invited Session "S21b-Energy-Efficient Connected Mobility" (TH-EA-T21), Thursday, November 20, 2025, 14:50−15:30, Surfers Paradise 3

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Abstract

This paper proposes a user-based dynamic pricing approach for attended home delivery (AHD), using marginal routing costs to improve efficiency and maximize profits. Delivery timing choices are modeled with a nested logit model, and multi-period vehicle routing problems (MPVRP) is modeled to simulate the vehicle routing. Three cost approximation methods—continuous approximation (CA), regression-based (RA), cheapest insertion (CI) are evaluated based on a MPVRP and the delivery timing choice model. Additionally, future order prediction mechanism is adopted to cope with future uncertainty. Numerical results show dynamic pricing is outperforming the fixed pricing, with all methods meeting speed requirements. After integrating the future prediction model, the profit increase across all approximation models. Additionally, the cluster location of customer is examined, finding that dynamic pricing could be more benefit when demand is clustered. This efficient approach offers a practical solution for user-based time slot pricing over larger areas.