Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Examining spatial heterogeneity of ridesourcing demand determinants with explainable machine learning

Xiaojian Zhang, Xiang Yan, Zhengze Zhou, Yiming Xu, Xilei Zhao

TL;DR

This study addresses how ridesourcing demand determinants vary nonlinearly across space by applying an explainable ML framework to Chicago OD pairs. It uses XGBoost, SHAP, and CPDP to quantify context-specific variable importance and uncover nonlinear relationships among built environment, sociodemographic, and transit-supply factors. Key findings show built-environment variables collectively drive prediction with context-dependent magnitudes (airport ≈50%, downtown ≈47%, neighborhood ≈41%), and nonlinear effects reveal distinct thresholds and effective ranges across contexts. The approach yields actionable, location-specific insights for transportation planning and ridesourcing management, while limitations point to the value of incorporating temporal and weather factors in future work.

Abstract

The growing significance of ridesourcing services in recent years suggests a need to examine the key determinants of ridesourcing demand. However, little is known regarding the nonlinear effects and spatial heterogeneity of ridesourcing demand determinants. This study applies an explainable-machine-learning-based analytical framework to identify the key factors that shape ridesourcing demand and to explore their nonlinear associations across various spatial contexts (airport, downtown, and neighborhood). We use the ridesourcing-trip data in Chicago for empirical analysis. The results reveal that the importance of built environment varies across spatial contexts, and it collectively contributes the largest importance in predicting ridesourcing demand for airport trips. Additionally, the nonlinear effects of built environment on ridesourcing demand show strong spatial variations. Ridesourcing demand is usually most responsive to the built environment changes for downtown trips, followed by neighborhood trips and airport trips. These findings offer transportation professionals nuanced insights for managing ridesourcing services.

Examining spatial heterogeneity of ridesourcing demand determinants with explainable machine learning

TL;DR

This study addresses how ridesourcing demand determinants vary nonlinearly across space by applying an explainable ML framework to Chicago OD pairs. It uses XGBoost, SHAP, and CPDP to quantify context-specific variable importance and uncover nonlinear relationships among built environment, sociodemographic, and transit-supply factors. Key findings show built-environment variables collectively drive prediction with context-dependent magnitudes (airport ≈50%, downtown ≈47%, neighborhood ≈41%), and nonlinear effects reveal distinct thresholds and effective ranges across contexts. The approach yields actionable, location-specific insights for transportation planning and ridesourcing management, while limitations point to the value of incorporating temporal and weather factors in future work.

Abstract

The growing significance of ridesourcing services in recent years suggests a need to examine the key determinants of ridesourcing demand. However, little is known regarding the nonlinear effects and spatial heterogeneity of ridesourcing demand determinants. This study applies an explainable-machine-learning-based analytical framework to identify the key factors that shape ridesourcing demand and to explore their nonlinear associations across various spatial contexts (airport, downtown, and neighborhood). We use the ridesourcing-trip data in Chicago for empirical analysis. The results reveal that the importance of built environment varies across spatial contexts, and it collectively contributes the largest importance in predicting ridesourcing demand for airport trips. Additionally, the nonlinear effects of built environment on ridesourcing demand show strong spatial variations. Ridesourcing demand is usually most responsive to the built environment changes for downtown trips, followed by neighborhood trips and airport trips. These findings offer transportation professionals nuanced insights for managing ridesourcing services.
Paper Structure (13 sections, 9 equations, 6 figures, 3 tables)

This paper contains 13 sections, 9 equations, 6 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Determinants of ridesourcing demand
  4. Approaches to identifying spatial heterogeneity
  5. Data
  6. Approach
  7. Modeling Ridesourcing Demand
  8. Interpreting the XGBoost model
  9. Results
  10. Descriptive Statistics
  11. Variable Importance
  12. Nonlinear Relationships
  13. Conclusion

Figures (6)

  • Figure 1: Spatial Distribution of three contexts
  • Figure 2: Variable Importance
  • Figure 3: Trip cost
  • Figure 4: The number of commuters
  • Figure 5: Key transit supply variables
  • ...and 1 more figures