Modeling Taxi Trip Generation Using GPS Data: The Montreal Case

With the emergence of new transport alternatives in the last decade, the taxi industry is struggling to keep its market share. Technological shift is one key element: taxi companies are implementing on-board GPS devices that produce large sets of data useful for strategic planning. There is currently no systematic processing of the available data to understand travel demand and this affects the ability to optimize the service. This article uses a month of GPS data from 1,000 taxis operating in Montreal to develop a taxi trip generation model. Daily taxi trips from and to each census tract are modeled using a multiple regression model in which variables describing demographic composition, land use features, transit availability and weather are used as explanatory variables. The performance of the final models is a R² =0.3300 for pickups and R² =0.5545 for drop-offs. Results reveal that the variables having the greater impact on taxi trips generation are income, age, transit access time, number of parking spots and, only affecting the drop-offs, job types. The research also provides a comparison between estimates of taxi trips using the 2008 large-scale Origin-Destination survey conducted in Montreal and the GPS data. The comparison reveals that some patterns are similar (temporal and distance distributions) but that the amount of trips differs a lot. It is not possible to draw full conclusion since the available taxi data are partials and that the survey only collects data from residents. Further analysis need to be conducted.

• Supplemental Notes:
  • This paper was sponsored by TRB committee AP060 Standing Committee on Paratransit. Alternate title: Modeling Taxi Trip Generation Using GPS Data: Montreal Case
• Corporate Authors:

  Transportation Research Board

  500 Fifth Street, NW
  Washington, DC  United States  20001
• Authors:
  • Lacombe, Annick
  • Morency, Catherine
• Conference:
  • Transportation Research Board 95th Annual Meeting
  • Location: Washington DC, United States
  • Date: 2016-1-10 to 2016-1-14
• Date: 2016

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; Maps; References; Tables;
• Pagination: 16p
• Monograph Title: TRB 95th Annual Meeting Compendium of Papers

Subject/Index Terms

• TRT Terms: Case studies; Data collection; Global Positioning System; Origin and destination; Taxi services; Trip generation
• Geographic Terms: Montreal (Canada)
• Subject Areas: Planning and Forecasting; Public Transportation; I72: Traffic and Transport Planning;

Filing Info

• Accession Number: 01590411
• Record Type: Publication
• Report/Paper Numbers: 16-4345
• Files: TRIS, TRB, ATRI
• Created Date: Feb 17 2016 12:01PM