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

TL;DR

This paper introduces MVGR-Net, a novel framework that enhances ride-hailing demand forecasting by learning comprehensive geospatial representations from web data and external events, significantly improving accuracy.

Contribution

The paper presents a two-stage framework combining multi-view geospatial representation learning with prompt-empowered LLM fine-tuning for improved forecasting accuracy.

Findings

Achieves state-of-the-art performance on DiDi datasets.

Effectively captures regional characteristics through multi-view learning.

Incorporates external events to improve demand prediction.

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.