Learning to Estimate Package Delivery Time in Mixed Imbalanced Delivery and Pickup Logistics Services

2024-10-29

SIGSPATIAL/GIS

AI Summary

In mixed pickup-and-delivery scenarios, inaccurate delivery-time prediction arises from low pickup volumes, stringent temporal constraints, deep spatiotemporal coupling, and the absence of rider mobility modeling. To address this, we propose TransPDT, a multi-task Transformer model. Its key contributions are: (1) a novel pattern-memory module that explicitly captures the strong influence of sparse pickups on rider decision-making; (2) joint routing prediction as an auxiliary task to enhance spatiotemporal sequence modeling for timeliness estimation; and (3) incorporation of rider spatial mobility priors to improve generalization under dynamic routing conditions. Evaluated on large-scale real-world logistics data from JD Logistics, TransPDT achieves significant gains in prediction accuracy. The system has been deployed in Beijing’s operational line, supporting real-time delivery-time estimation for over 2,000 riders and hundreds of thousands of packages daily.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Application Domains: Transportation
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Accurately estimating package delivery time is essential to the logistics industry, which enables reasonable work allocation and on-time service guarantee. This becomes even more necessary in mixed logistics scenarios where couriers handle a high volume of delivery and a smaller number of pickup simultaneously. However, most of the related works treat the pickup and delivery patterns on couriers' decision behavior equally, neglecting that the pickup has a greater impact on couriers' decision-making compared to the delivery due to its tighter time constraints. In such context, we have three main challenges: 1) multiple spatiotemporal factors are intricately interconnected, significantly affecting couriers' delivery behavior; 2) pickups have stricter time requirements but are limited in number, making it challenging to model their effects on couriers' delivery process; 3) couriers' spatial mobility patterns are critical determinants of their delivery behavior, but have been insufficiently explored. To deal with these, we propose TransPDT, a Transformer-based multi-task package delivery time prediction model. We first employ the Transformer encoder architecture to capture the spatio-temporal dependencies of couriers' historical travel routes and pending package sets. Then we design the pattern memory to learn the patterns of pickup in the imbalanced dataset via attention mechanism. We also set the route prediction as an auxiliary task of delivery time prediction, and incorporate the prior courier spatial movement regularities in prediction. Extensive experiments on real industry-scale datasets demonstrate the superiority of our method. A system based on TransPDT is deployed internally in JD Logistics to track more than 2000 couriers handling hundreds of thousands of packages per day in Beijing.

Problem

• Estimating delivery time in mixed pickup-delivery logistics with imbalanced data
• Modeling pickup's greater impact on courier decisions due to tight time constraints
• Capturing spatiotemporal dependencies and courier mobility patterns for accurate predictions

Innovation

• Transformer encoder captures spatio-temporal dependencies
• Pattern memory learns pickup patterns via attention
• Route prediction as auxiliary task enhances accuracy