Examining the Nonlinear Impacts of Origin-Destination Built Environment on Metro Ridership at Station-to-Station Level

Although many studies have explored the relationship between built environment and metro ridership, literature offers limited evidence on nonlinear effect of origin destination environments station-to-station ridership. Using data from Chongqing, this study uses gradient boosting decision trees (GBDT) model to explore impact The research results show that at has a greater ridership than destination. All independent variables examined complex effects threshold distance city center, number companies, building volume rate positive both provide suggestions for optimizing around stations.