A holistic approach for modeling and predicting bike demand
作者：
Highlights：
• Handling unexpected bike demand during large city situations.
• Modeling bike demand during casual and regular days.
• Prediction during regular days using Gradient Boosted Regression Trees.
• Prediction during large city situations incorporating Holtz’s trend forecasting technique.
• A polynomial algorithm for efficient bike relocation.
摘要
•Handling unexpected bike demand during large city situations.•Modeling bike demand during casual and regular days.•Prediction during regular days using Gradient Boosted Regression Trees.•Prediction during large city situations incorporating Holtz’s trend forecasting technique.•A polynomial algorithm for efficient bike relocation.
论文关键词：Bike sharing systems,Rebalancing,Modeling,Prediction
论文评审过程：Received 23 May 2022, Revised 16 September 2022, Accepted 17 September 2022, Available online 27 September 2022, Version of Record 7 October 2022.
论文官网地址：https://doi.org/10.1016/j.is.2022.102129
