RideBench: A Large-Scale Exogenous-Aware Benchmark for Ride-Hailing Time Series Forecasting

Key points

• Ride-Hailing spans four consecutive years at half-hourly granularity and covers three representative exogenous scenarios: Weather Disturbance, Holiday Effect, and Large-scale Event Impact.1
• Built upon Ride-Hailing, we introduce RideBench, a comprehensive benchmark for exogenous-aware ride-hailing forecasting, covering both regular week-ahead forecasting and long-horizon 8-week-ahead forecasting with up to 2,688 prediction steps.1
• Our results show that future-known exogenous variables provide clear benefits in regular week-ahead forecasting, especially under weather, holiday, and large-scale event (e.g., major sporting events and concerts) scenarios.1
• By introducing Ride-Hailing and RideBench, we aim to encourage the community to study these practical challenges in real-world ride-hailing forecasting.1

Sources (1)

• [1]RideBench: A Large-Scale Exogenous-Aware Benchmark for Ride-Hailing Time Series Forecasting
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 03:23 AM

  We release Ride-Hailing, a large-scale ride-hailing time series dataset synthesized from DiDi's marketplace data across 200 spatial areas.

  Ride-Hailing spans four consecutive years at half-hourly granularity and covers three representative exogenous scenarios: Weather Disturbance, Holiday Effect, and Large-scale Event Impact.

Extractive summary: sentences quoted from the sources.