Interpretable GBDT Model for Analysing Ridership Mechanisms in Urban Rail Transit: A Case Study in Shenzhen

Abstract

With the acceleration of urbanisation and the diversification of residents’ travel needs, rail transit plays a critical role in mitigating traffic congestion. However, existing studies predominantly rely on linear models, neglecting the nonlinear effects and spatial heterogeneity of built environment factors on ridership. To address this gap, this study integrates the Multiscale Geographically Weighted Regression (MGWR) model and the Gradient Boosting Decision Tree (GBDT) model to analyse the impact of built environment factors on total, inbound, and outbound ridership in Shenzhen. Utilising Automatic Fare Collection (AFC) data and multiple built environment variables, we identify six key factors (office type, accessibility, road network density, floor area ratio (FAR), public services, and residential type) through SHapley Additive exPlanations (SHAP) value and partial dependency plot (PDP) analysis. Notably, this study constructs a three-dimensional PDP to explore the linkage effects of building volume ratio and accessibility, revealing their joint influence on ridership. The results demonstrate that the GBDT model outperforms MGWR in handling high-dimensional nonlinear data. This paper provides policy recommendations for transport authorities, highlighting the synergies between optimising the planning of the built environment and the development of rail transport to improve the efficiency of short-distance commuting while supporting long-distance cross-city travel.