Temporal & Spatial Analysis of Taxi Demand in Montréal, Using a Clustering Approach

Taxi fleet equipped with global positioning system (GPS) tracking devices can provide many insights on when and where taxis are used. Analyzing daily distribution of the hourly number of taxi trips at a district level can help the taxi industry and transport planners to better understand the spatial-temporal structure of taxi trip demand. This paper uses a K-Means algorithm to classify day-district normalized distributions of taxi trips as well as a set of descriptive variables to understand resulting clusters. Results suggest that daily profiles are mostly segmented based on the relative importance of evening and overnight demand and to a lesser extent on work-related diurnal demand. This hints at why socio-economically different districts have similar demand distributions. The paper concludes by showing the complementary effect of temperature and seasons on cluster composition.

  • Supplemental Notes:
    • This paper was sponsored by TRB committee AP060 Standing Committee on Paratransit. Alternate title: Temporal and Spatial Analysis of Taxi Demand in Montréal, Canada, Using Clustering Approach
  • Corporate Authors:

    Transportation Research Board

    500 Fifth Street, NW
    Washington, DC  United States  20001
  • Authors:
    • Laviolette, Jerome
    • Morency, Catherine
    • Saunier, Nicolas
    • Lacombe, Annick
    • Douakha, Khalid
  • Conference:
  • Date: 2017


  • English

Media Info

  • Media Type: Digital/other
  • Features: Figures; Maps; References; Tables;
  • Pagination: 14p
  • Monograph Title: TRB 96th Annual Meeting Compendium of Papers

Subject/Index Terms

Filing Info

  • Accession Number: 01626169
  • Record Type: Publication
  • Report/Paper Numbers: 17-00219
  • Files: TRIS, TRB, ATRI
  • Created Date: Feb 17 2017 9:04AM