Research on the Spatiotemporal Heterogeneity in the Impact of the Built Environment on Ridesplitting Demand

To explore the spatiotemporal heterogeneity in the impact of the built environment on ridesplitting demand, this paper proposes an analysis method based on multi-source data for the spatiotemporal impact mechanism of ridesplitting demand. First, an improved grid generation method is adopted to refine the study area, in order to reduce the impact of boundary effects on the analysis results. Then, three research periods are determined: afternoon peak, evening peak, and late-night peak. Next, based on the “5D” framework, the influencing factors of the built environment are quantified. Finally, a multi-scale geographically weighted regression model (MGWR) is constructed to reveal the spatiotemporal heterogeneity of the impact mechanism. An empirical study is conducted in Xi’an as an example. The results show that the MGWR model has the good fitness and explanatory power, capable of effectively capturing the different influence scales of explanatory variables on ridesplitting demand. The research results are beneficial for ride-hailing companies to optimize ridesplitting incentive strategies from a spatiotemporally differentiated perspective to promote the low-carbon transformation of the industry.