Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 131 - The Future of Transportation: The Predicting Power of Driver Behavior Data
Type: Topic Contributed
Date/Time: Monday, August 3, 2020 : 1:00 PM to 2:50 PM
Sponsor: Transportation Statistics Interest Group
Abstract #310988
Title: Ride-Hailing Driver Risk Assessment
Author(s): Chen Qian*
Keywords: Ride-hailing drivers; Crash risk prediction; Operational characteristics; General Addictive Models

The rise of ride-hailing service in the last decade provides an efficient travel mode by matching drivers and travelers via smartphone apps. Millions of non-taxi drivers can provide travel service but also bring safety concerns due to heterogeneity in driver population. This study evaluates crash risk factors for ride-hailing drivers using a sample of more than 150,000 drivers, including crash history and ride-hailing operational characteristics, We utilize the Poisson Generalized Additive Model to accommodate the potential nonlinear relationship between crash rate and risk factors. We adopt the SHapley Additive exPlanation (SHAP) method to assess and visualize the contribution of each risk factor. The results indicate that crash history, years of being a ride-hailing driver, and total driving distance are the leading factors contributing to ride-hailing driver crash risk. The results of this study provide insight on crash risk for ride-hailing drivers and provide critical information for developing safety countermeasure, ride-hailing driver education programs, as well as safety policy for ride-hailing service industry.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2020 program