Multi-group exploration of the built environment and metro ridership: Comparison of commuters, seniors and students

Abstract

Understanding the associations between demographic groups’ metro travel behaviors and the built environment is crucial for addressing automobile dependence and promoting transportation equity and reasonable urban construction. This study examines the nonlinear relationships and threshold effects of the built environment on the metro travel patterns of three groups (i.e., commuters, seniors, and students) by applying smart card data in Kunming, China. We select the optimal machine learning model—gradient boosting decision trees (GBDTs)—and consider various built environment attributes. Our findings indicate that: 1) built environment attributes universally have nonlinear and threshold effects on metro travel for all groups; 2) the collective contributions of density and diversity differ greatly across groups compared to other attributes; and 3) only a few built environment attributes have similar effect directions and degrees across all three groups, while most have unique effects on each group. The findings suggest metro station area planning strategies to promote metro use and transportation equity for different groups.