Classifying Behavioral Dynamics of Taxi Drivers Route Choices Using Longitudinal GPS Data

This study aims to capture the behavioral heterogeneity in route choice by identifying subgroups of drivers based on their actual route choices and factors affecting them. The authors have studied a highly longitudinal global positioning system (GPS) dataset, tracking 1,746 taxi drivers over a period of one year, making more than 22,000 trips between the Islands of Montreal and Laval. The authors opted for a two-step procedure, where in the first step a Principal Component Analysis (PCA) is performed to reduce collinearity among attributes, followed by a Hierarchical Agglomerative Clustering (HAC) to form behavioral clusters in the second step. Results show that four major types of route choice behaviors are observable among taxi drivers. These clusters show significant variations based on the time of day (day/night) and the traveled distance (shorter trips/longer trips) and are labelled: “Short trips night drivers”, “Long trips night drivers”, “Short trips day drivers”, and “Long trips day drivers”. Due to the rise of ride-hailing services, the understanding of these patterns are important for city and transportation planners in the context of proposing new laws and policies that safeguard taxi industry as well as encourage sharing economy. The inclusion of similar typologies in route choice models would improve their behavioral aspect as well as their estimation and prediction abilities.

• 
• Supplemental Notes:
  • This paper was sponsored by TRB committee AP060 Standing Committee on Paratransit. Alternate title: Classifying Behavioral Dynamics of Taxi Drivers' Route Choices Using Longitudinal GPS Data
• Corporate Authors:

  Transportation Research Board

  500 Fifth Street, NW
  Washington, DC  United States  20001
• Authors:
  • Alizadeh, Hamzeh
  • Farooq, Bilal
  • Morency, Catherine
  • Saunier, Nicolas
• Conference:
  • Transportation Research Board 96th Annual Meeting
  • Location: Washington DC, United States
  • Date: 2017-1-8 to 2017-1-12
• Date: 2017

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; Maps; References; Tables;
• Pagination: 17p
• Monograph Title: TRB 96th Annual Meeting Compendium of Papers

Subject/Index Terms

• TRT Terms: Behavior; Cluster analysis; Global Positioning System; Longitudinal studies; Route choice; Statistical analysis; Taxicab drivers
• Uncontrolled Terms: Principal component analysis
• Subject Areas: Data and Information Technology; Highways; Planning and Forecasting; Public Transportation;

Filing Info

• Accession Number: 01631140
• Record Type: Publication
• Report/Paper Numbers: 17-05190
• Files: PRP, TRIS, TRB, ATRI
• Created Date: Mar 29 2017 9:23AM