Identifying key factors associated with ridesplitting adoption rate and modeling their nonlinear relationships

Ridesharing is critical for promoting transportation sustainability. As a new form of ridesharing services, ridesplitting has rarely been studied. Based on the Chicago ridesourcing trip data, this study explores how ridesplitting adoption rate (i.e., the proportion of ridesourcing trips with ridesharing authorization) varies across space and what factors are associated with these variations. The authors find large variations in ridesplitting adoption rates across neighborhoods (Census Tracts) and across origin–destination (Census-Tract-to-Census-Tract) pairs. Particularly, the ridesplitting adoption rate is low for airport rides. The authors further apply a random forest model to explore which factors are key predictors of ridesplitting adoption rate across O-D pairs and to explore their nonlinear associations. The results suggest that the socioeconomic and demographic variables collectively contribute to 68.60% of the predictive power of the model, but travel-cost variables and built-environment-related factors are also important. The most important variables associated with ridesplitting adoption are ethnic composition, median household income, education level, trip distance, and neighborhood density. The authors further examine the nonlinear association between neighborhood ridesplitting adoption rate and several key variables such as the percentage of white population, median household income, and neighborhood Walk Score. The revealed nonlinear patterns can help transportation professionals identify neighborhoods with the greatest potential to promote ridesplitting.

• Record URL:
  • https://doi.org/10.1016/j.tra.2020.12.005
• Record URL:
  • http://www.sciencedirect.com/science/article/pii/S0965856420307989
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/09658564
• Supplemental Notes:
  • © 2020 Elsevier Ltd. All rights reserved. Abstract reprinted with permission of Elsevier.
• Authors:
  • Xu, Yiming
  • Yan, Xiang
  • Liu, Xinyu
  • Zhao, Xilei
• Publication Date: 2021-2

Language

• English

Media Info

• Media Type: Web
• Features: Appendices; Figures; References; Tables;
• Pagination: pp 170-188
• Serial:
  • Transportation Research Part A: Policy and Practice
  • Volume: 144
  • Issue Number: 0
  • Publisher: Elsevier
  • ISSN: 0965-8564
  • Serial URL: http://www.sciencedirect.com/science/journal/09658564

Subject/Index Terms

• TRT Terms: Attitudes; Decision trees; Households; Income; Machine learning; Neighborhoods; Nonlinear systems; Persons by educational level; Persons by race and ethnicity; Ridesharing
• Subject Areas: Highways; Operations and Traffic Management; Planning and Forecasting; Public Transportation; Society;

Filing Info

• Accession Number: 01767725
• Record Type: Publication
• Files: TRIS
• Created Date: Mar 23 2021 11:13AM