Enhancing Ride-Hailing Forecasting at DiDi with Multi-View Geospatial Representation Learning from the Web
This work addresses ride-hailing forecasting for optimizing urban mobility and passenger experience, representing an incremental improvement through a novel hybrid method.
The paper tackles ride-hailing forecasting challenges like geospatial heterogeneity and external events by proposing MVGR-Net, a two-stage framework that integrates multi-view geospatial representations and fine-tunes Large Language Models, achieving state-of-the-art performance on DiDi's datasets.
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.