The Nonlinear and Threshold Effect of Built Environment on Ride-Hailing Travel Demand
Source abstract
Abstract
While numerous studies have explored the correlation between the built environment and ride-hailing demand, few have assessed their nonlinear interplay. Utilizing ride-hailing order data and multi-source built environment data from Nanjing, China, this paper uses the machine learning method, eXtreme Gradient Boosting (XGBoost), combined with Shapley Additive exPlanations (SHAP) and Partial Dependence Plots (PDPs) to investigate the impact of built environment factors on ride-hailing travel demand, including their nonlinear and threshold effects. The findings reveal that dining facilities have the most significant impact, with a contribution rate of 30.75%, on predicting ride-hailing travel demand. Additionally, financial, corporate, and medical facilities also exert considerable influence. The built environment factors need to reach a certain threshold or within a certain range to maximize the impact of ride-hailing travel demand. Population density, land use mix, and distance to the subway station collectively influence ride-hailing demand. The results are helpful for TNCs to allocate network ride-hailing resources reasonably and effectively.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Transportation and Mobility Innovations · Urban Transport and Accessibility · Transportation Planning and Optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Automobile and Traffic Engineering, Nanjing Forestry University, Nanjing 210037, China
Funding
Postgraduate Research & Practice Innovation Program of Jiangsu Province
References (46)
Show source-provided references
1. Just a better taxi? A survey-based comparison of taxis, transit, and ridesourcing services in San Francisco10.1016/j.tranpol.2015.10.004 ↗
2. Measuring when Uber behaves as a substitute or supplement to transit: An examination of travel-time differences in Toronto10.1016/j.jtrangeo.2019.102629 ↗
3. Analysis on spatiotemporal urban mobility based on online car-hailing data10.1016/j.jtrangeo.2019.102568 ↗
4. The influence of ride-hailing on travel frequency and mode choice10.1016/j.trd.2021.103125 ↗
5. Impacts of built environment on commuting mode choice considering spatial autocorrelation
6. Exploring the relationships of the residential and workplace built environment with commuting mode choice: A hierarchical cross-classified structural equation model10.1080/19427867.2020.1857010 ↗
7. Yin, C., Wang, X., Shao, C., and Ma, J. (2022). Exploring the Relationship between Built Environment and Commuting Mode Choice: Longitudinal Evidence from China. Int. J. Environ. Res. Public Health, 19.10.3390/ijerph192114149 ↗
8. Spatiotemporal exploration of the non-linear impacts of accessibility on metro ridership10.1016/j.jtrangeo.2022.103380 ↗
9. Nonlinear, threshold and synergistic effects of first/last-mile facilities on metro ridership10.1016/j.trd.2023.103856 ↗
10. Examining the spatial-temporal relationship between urban built environment and taxi ridership: Results of a semi-parametric GWPR model10.1016/j.jtrangeo.2021.103172 ↗
11. Spatial variation of the urban taxi ridership using GPS data10.1016/j.apgeog.2015.02.011 ↗
12. Zhu, P., Li, J., Wang, K., and Huang, J. (2023). Exploring spatial heterogeneity in the impact of built environment on taxi ridership using multiscale geographically weighted regression. Transportation.10.1007/s11116-023-10393-1 ↗
13. A comparison in travel patterns and determinants of user demand between docked and dockless bike-sharing systems using multi-sourced data10.1016/j.tra.2020.06.022 ↗
14. Spatial-temporal heterogeneity and built environment nonlinearity in inconsiderate parking of dockless bike-sharing
15. Exploring the effects of the built environment on commuting mode choice in neighborhoods near public transit stations: Evidence from China10.1080/03081060.2020.1851453 ↗
16. Wang, X., Shao, C., Yin, C., and Zhuge, C. (2018). Exploring the Influence of Built Environment on Car Ownership and Use with a Spatial Multilevel Model: A Case Study of Changchun, China. Int. J. Environ. Res. Public Health, 15.10.3390/ijerph15091868 ↗
17. Exploring the impact of built environment on car use: Does living near urban rail transit matter?10.1080/19427867.2019.1611196 ↗
18. Spatial variation in shared ride-hail trip demand and factors contributing to sharing: Lessons from Chicago10.1016/j.jtrangeo.2020.102944 ↗
19. Geographically Weighted Regression: A Natural Evolution of the Expansion Method for Spatial Data Analysis10.1068/a301905 ↗
20. Exploring the spatially heterogeneous effect of the built environment on ride-hailing travel demand: A geographically weighted quantile regression model10.1016/j.tbs.2022.05.004 ↗
21. Variation in ride-hailing trips in Chengdu, China10.1016/j.trd.2020.102596 ↗
22. Exploring the spatial variation of ridesourcing demand and its relationship to built environment and socioeconomic factors with the geographically weighted Poisson regression10.1016/j.jtrangeo.2019.01.004 ↗
23. Understanding cycling distance according to the prediction of the XGBoost and the interpretation of SHAP: A non-linear and interaction effect analysis10.1016/j.jtrangeo.2022.103414 ↗
24. Exploring nonlinear and collective influences of regional and local built environment characteristics on travel distances by mode10.1016/j.jtrangeo.2023.103599 ↗
25. Exploring nonlinear effects of the built environment on ridesplitting: Evidence from Chengdu10.1016/j.trd.2021.102776 ↗
26. Modeling determinants of ridesourcing usage: A census tract-level analysis of Chicago10.1016/j.trc.2020.102769 ↗
27. Adoption and frequency of use of ride-hailing services in a European city: The case of Madrid10.1016/j.trc.2021.103359 ↗
28. Trade Uber for the Bus? An Investigation of Individual Willingness to Use Ride-Hail Versus Transit10.1080/01944363.2019.1687318 ↗
29. Examining the influence of attitudinal factors on the use of ride-hailing services in Toronto10.1016/j.tra.2021.02.002 ↗
30. Travel and the Built Environment: A meta-analysis10.1080/01944361003766766 ↗
31. Travel and the Built Environment: A Synthesis10.3141/1780-10 ↗
32. What influences travelers to use Uber? Exploring the factors affecting the adoption of on-demand ride services in California10.1016/j.tbs.2018.06.002 ↗
33. Exploring the influence of built environment on Uber demand10.1016/j.trd.2020.102296 ↗
34. Nonlinear effects of residential and workplace built environment on car dependence10.1016/j.jtrangeo.2021.103207 ↗
35. Research on Nonlinear Associations and Interactions for Short-Distance Travel Mode Choice of Car Users10.1155/2022/8598320 ↗
36. Nonlinear effects of the built environment on metro-integrated ridesourcing usage10.1016/j.trd.2022.103426 ↗
37. (2023, October 12). Statistical Communiqué on National Economic and Social Development of Nanjing in 2022, Available online: https://tjj.nanjing.gov.cn/bmfw/njsj/202303/t20230324_3871176.html.
38. Portraying ride-hailing mobility using multi-day trip order data: A case study of Beijing, China10.1016/j.tra.2021.01.017 ↗
39. Understanding the spatiotemporal variation of ride-hailing orders under different travel distances10.1016/j.tbs.2023.100581 ↗
40. Zhao, F., Ma, J., Yin, C., Tang, W., Wang, X., and Yin, J. (2024). Spatiotemporal Heterogeneous Effects of Built Environment and Taxi Demand on Ride-Hailing Ridership. Appl. Sci., 14.10.3390/app14010142 ↗
41. Chen, T., Guestrin, C., and Assoc Comp, M. (2016, January 13–17). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), San Francisco, CA, USA.10.1145/2939672.2939785 ↗
42. Shapley, L.S. (1952). A Value for N-Person Games, RAND Corporation.
43. Lundberg, S., and Lee, S.-I. (2017, January 4–9). A Unified Approach to Interpreting Model Predictions. Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS’17), Long Beach, CA, USA.
44. Explaining prediction models and individual predictions with feature contributions10.1007/s10115-013-0679-x ↗
45. Extracting spatial effects from machine learning model using local interpretation method: An example of SHAP and XGBoost10.1016/j.compenvurbsys.2022.101845 ↗
46. A multiscale spatial analysis of taxi ridership10.1016/j.jtrangeo.2023.103718 ↗