Joint Matching and Pricing for Crowd-shipping with In-store Customers

2025-07-02

AI Summary

To address high last-mile delivery costs and stringent time constraints in urban retail settings, this paper proposes a centralized collaborative optimization framework that leverages in-store customers as crowd-sourced couriers. We formulate the problem as a Markov decision process and integrate neural approximate dynamic programming (NeurADP) with a deep double Q-network (DDQN) to jointly optimize order assignment, dynamic pricing, multi-destination route planning, and flexible delayed delivery. To our knowledge, this is the first approach enabling adaptive, end-to-end co-optimization of these interdependent decisions. Experimental results demonstrate that our method reduces delivery costs by 6.7% over fixed-pricing baselines and by 18% over myopic policies. Moreover, incorporating flexible delivery windows and multi-stop routing further decreases operational expenses by 8% and 17%, respectively—substantially enhancing system robustness and practical deployability in real-world urban retail environments.

Technology Category

• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Ad search and search for Web retail
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

This paper examines the use of in-store customers as delivery couriers in a centralized crowd-shipping system, targeting the growing need for efficient last-mile delivery in urban areas. We consider a brick-and-mortar retail setting where shoppers are offered compensation to deliver time-sensitive online orders. To manage this process, we propose a Markov Decision Process (MDP) model that captures key uncertainties, including the stochastic arrival of orders and crowd-shippers, and the probabilistic acceptance of delivery offers. Our solution approach integrates Neural Approximate Dynamic Programming (NeurADP) for adaptive order-to-shopper assignment with a Deep Double Q-Network (DDQN) for dynamic pricing. This joint optimization strategy enables multi-drop routing and accounts for offer acceptance uncertainty, aligning more closely with real-world operations. Experimental results demonstrate that the integrated NeurADP + DDQN policy achieves notable improvements in delivery cost efficiency, with up to 6.7% savings over NeurADP with fixed pricing and approximately 18% over myopic baselines. We also show that allowing flexible delivery delays and enabling multi-destination routing further reduces operational costs by 8% and 17%, respectively. These findings underscore the advantages of dynamic, forward-looking policies in crowd-shipping systems and offer practical guidance for urban logistics operators.

Problem

• Optimizing last-mile delivery using in-store customers as couriers
• Managing uncertainties in order and crowd-shipper arrivals dynamically
• Reducing operational costs through adaptive pricing and routing strategies

Innovation

• MDP model for order and crowd-shipper uncertainties
• NeurADP for adaptive order-to-shopper assignment
• DDQN for dynamic pricing optimization