Highlights Examined the spatiotemporal pattern of BSS using random forest with PDP. Analyzed the relative importance of influencing factors across different scenarios. Revealed the nonlinear and threshold effect of built environment factors. Compared the heterogeneous impact of influencing factors between study areas.
Abstract To better understand dockless bike-sharing (DBS) usage and advance the knowledge on shared bicycle service, this study empirically investigated the riding behavior in the time and space dimensions based on multisource datasets. Taking Central Business District (CBD) and Beijing West Railway Station (BWRS) as study areas, this study analyzed and compared the DBS usage based on the traffic grid between the two study areas. Furthermore, the random forest (RF) model was applied to investigate the contribution of influencing factors on origin/ destination and origin–destination pair trip volume. Partial Dependence Plots (PDP) analysis was conducted to explore the nonlinear effects of influencing factors. Results show considerable variation across different scenarios. Variables such as government agencies, restaurants, bus stop distance, and metro distance show nonlinear and threshold effects on DBS usage. The findings offer valuable insights for urban infrastructure development and bike rebalancing strategies, and the formulation of green and sustainable transportation policies.
Nonlinear effects of factors on dockless bike-sharing usage considering grid-based spatiotemporal heterogeneity
2022-01-20
Article (Journal)
Electronic Resource
English
Understanding the usage of dockless bike sharing in Singapore
Taylor & Francis Verlag | 2018
|Forecasting usage and bike distribution of dockless bike-sharing using journey data
IET | 2020
|Dockless bike-sharing systems: what are the implications?
Taylor & Francis Verlag | 2020
|