Abstract
•Models of trip generation for ride-hailing in Chengdu, China are estimated.•The built environment and subways are associated with ride-hailing trip generation.•Passenger transportation hubs are associated with ride-hailing trips in most cases.•Recreational points have greater impacts on drop-offs in the evening peak and late night.•Subways and land-use mix are negatively associated with the elasticity of population density.
We investigate various spatial, economic, and land-use factors associated with the generation of trips for ride-hailing services in Chengdu, China. Using one month of data for DiDi Chuxing trips in Chengdu, we characterize the unique pattern of TNC ride-hailing trips over space and for different time periods. We examine the association between the generation of ride-hailing trips and spatial characteristics, including population density, floor-area ratio, housing prices, road networks, the proximity of public transit, land use mix, and points of interests. We estimate “global” regression models and “local” Geographically Weighted Regression models that account for the spatial variation of each factor on trip generation. Results suggest that population density, local road density, floor-area ratio, housing price, and the proximity to subways have positive associations with DiDi trip generation. We also examine the spatial variation associated with the local population density coefficients which vary throughout the city.