Exploring the influence of built environment on demand of online car-hailing travel using multi-scale geographically temporal weighted regression model

Abstract

The demand for online car-hailing travel is influenced by the built environment, which exhibits spatio-temporal heterogeneity in its impact. Previous studies have commonly employed geographically weighted regression (GWR) model and geographically temporal weighted regression (GTWR) model to examine the relationship between demand for online car-hailing trips and built environment. However, these studies have overlooked the scales of influence different built environment variables. This study addressed this issue by considering scale effects based on GTWR to form the multi-scale geographically temporal weighted regression (MGTWR) to explore the spatio-temporal impact of the urban built environment on the demand for online car-hailing trips. An empirical study was conducted to assess the effectiveness of MGTWR model using Point of Interest (POI) data and online car-hailing orders data in Haikou. The evaluation indicators showed that the MGTWR model has higher accuracy in fitting than the GTWR model. Moreover, the impact of each type of POI on demand of online car-hailing travel was analyzed by examining the temporal and spatial distribution of the regression coefficients.