Summary
Predicting how many ride-hailing rides people will request is hard because many outside factors like weather, holidays, or big events affect demand. The authors created Ride-Hailing, a large dataset showing ride requests every half hour over four years and covering these important outside influences. They then built RideBench, a test platform that checks how well different forecasting methods handle these outside factors and make predictions for both short and long periods ahead. Their tests show that while having future information like weather helps predictions, current methods still struggle to handle complex changes and long-term forecasts well. This reveals there is room for better tools to improve ride-hailing predictions in real-world situations.
What this means in practice
- •For ride-hailing service teams: Improve demand prediction systems by testing how well methods handle weather, holidays, and events for short- and long-term ride forecasts.
- •For public transit planners: Use exogenous-aware forecasting models evaluated on RideBench to better anticipate transportation demand during major events and disturbances.
Authors
Shengsheng Lin, Jing Hu, Zhengyang Hu, Jiazheng Sun, Zichun Cao, Siwei Sun, Zhichao Zou, Enyun Yu, Dongdong Li, Xinyi Hu, Weiwei Lin
Abstract
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. 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. RideBench evaluates over 30 representative forecasting methods, including endogenous-only models, exogenous-aware models, and time series foundation models. 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. However, current exogenous-aware models still struggle to fully capture disturbance-induced pattern changes under complex external contexts. For long-horizon forecasting, existing models cannot simultaneously achieve low pointwise errors, accurate broad trends, and reliable near-term forecasts. These findings reveal a clear mismatch between existing forecasting models and real-world ride-hailing requirements, highlighting the need for models that can better exploit future-known exogenous information, scale across heterogeneous areas, and support long-horizon planning. By introducing Ride-Hailing and RideBench, we aim to encourage the community to study these practical challenges in real-world ride-hailing forecasting.