MRGRP: Empowering Courier Route Prediction in Food Delivery Service with Multi-Relational Graph

2025-05-17

AI Summary

To address low prediction accuracy in rider route planning for on-demand food delivery—where heuristic methods ignore rider preferences and learning-based approaches struggle to model multi-source heterogeneous dependencies—this paper proposes GraphFormer. First, it constructs a fine-grained multi-relational graph that explicitly encodes spatial, temporal, and pickup-delivery dependencies among orders. Second, it designs a routing decoder integrating rider profiling with dynamic spatiotemporal context. Third, it incorporates high-quality historical routes as reference sequences to enhance generalization. Experiments demonstrate state-of-the-art performance in offline evaluation; upon deployment on Meituan’s Turing platform, GraphFormer achieves a prediction accuracy of 0.819, significantly outperforming baseline heuristic algorithms. The core contributions are: (i) the first multi-relational graph modeling paradigm for delivery routing, and (ii) a novel graph neural network–Transformer hybrid architecture explicitly tailored to rider behavioral patterns.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Heuristic Search

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Instant food delivery has become one of the most popular web services worldwide due to its convenience in daily life. A fundamental challenge is accurately predicting courier routes to optimize task dispatch and improve delivery efficiency. This enhances satisfaction for couriers and users and increases platform profitability. The current heuristic prediction method uses only limited human-selected task features and ignores couriers preferences, causing suboptimal results. Additionally, existing learning-based methods do not fully capture the diverse factors influencing courier decisions or the complex relationships among them. To address this, we propose a Multi-Relational Graph-based Route Prediction (MRGRP) method that models fine-grained correlations among tasks affecting courier decisions for accurate prediction. We encode spatial and temporal proximity, along with pickup-delivery relationships, into a multi-relational graph and design a GraphFormer architecture to capture these complex connections. We also introduce a route decoder that leverages courier information and dynamic distance and time contexts for prediction, using existing route solutions as references to improve outcomes. Experiments show our model achieves state-of-the-art route prediction on offline data from cities of various sizes. Deployed on the Meituan Turing platform, it surpasses the current heuristic algorithm, reaching a high route prediction accuracy of 0.819, essential for courier and user satisfaction in instant food delivery.

Problem

• Predicting courier routes accurately to optimize food delivery efficiency
• Capturing diverse factors and complex relationships influencing courier decisions
• Improving route prediction accuracy using multi-relational graph modeling

Innovation

• Multi-Relational Graph models task correlations
• GraphFormer captures spatial-temporal-proximity relationships
• Route decoder integrates courier and dynamic contexts