Enhancing Ride-Hailing Forecasting at DiDi with Multi-View Geospatial Representation Learning from the Web

2026-02-11

AI Summary

This work proposes MVGR-Net, a novel framework addressing the challenges of spatial heterogeneity and external event interference in ride-hailing demand forecasting. The approach uniquely integrates multi-view geographic representation learning with large language model (LLM) prompting: during pretraining, it constructs rich geographic semantic representations by jointly modeling points of interest (POIs) and spatiotemporal mobility patterns; during inference, it leverages prompt engineering to fine-tune the LLM for dynamically incorporating external event information. Extensive experiments on real-world DiDi datasets demonstrate that MVGR-Net significantly outperforms state-of-the-art methods, achieving industry-leading prediction accuracy and effectively enhancing both fleet dispatch efficiency and user experience.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The proliferation of ride-hailing services has fundamentally transformed urban mobility patterns, making accurate ride-hailing forecasting crucial for optimizing passenger experience and urban transportation efficiency. However, ride-hailing forecasting faces significant challenges due to geospatial heterogeneity and high susceptibility to external events. This paper proposes MVGR-Net(Multi-View Geospatial Representation Learning), a novel framework that addresses these challenges through a two-stage approach. In the pretraining stage, we learn comprehensive geospatial representations by integrating Points-of-Interest and temporal mobility patterns to capture regional characteristics from both semantic attribute and temporal mobility pattern views. The forecasting stage leverages these representations through a prompt-empowered framework that fine-tunes Large Language Models while incorporating external events. Extensive experiments on DiDi's real-world datasets demonstrate the state-of-the-art performance.

Problem

• ride-hailing forecasting
• geospatial heterogeneity
• external events
• urban mobility
• demand prediction

Innovation

• Multi-View Geospatial Representation
• Prompt-based Forecasting
• Large Language Model Fine-tuning
• Ride-hailing Demand Prediction
• Spatiotemporal Heterogeneity