Waze Pilot: Explore the Possibilities of Using Data for Safety Applications
Better Understand and Mitigate Crash Risk by Integrating Public and Private Data Sources
Crowdsourced mobile applications such as Waze can provide real-time and historical data about roadway conditions, when and where users are active. Analytical methods were used to test an application of Waze traffic alerts to a crash prediction model used to guide Tennessee law enforcement resource allocation. To target locations and times more accurately with a high crash propensity, the potential for Waze alerts to improve the temporal and spatial resolution of the model was assessed. Using the Waze data, the spatial resolution of crash estimates was refined from 42 to 1 square miles, and the temporal resolution was refined from 4 to 1-hour time windows, while improving accuracy. The model’s incorporation of crowdsourced data has shown potential for similar types of data-driven safety approaches elsewhere. SDC enabled the integration of public and private data sources to support these analytical approaches.
1. Flynn DFB, Gilmore MM, Dolan JP, Teicher P, Sudderth EA. Using Crowdsourced Data to Improve Models of Traffic Crash Propensity: Tennessee Highway Patrol Case Study. Transportation Research Record. March 2022. doi:10.1177/03611981221083305
https://journals.sagepub.com/doi/10.1177/03611981221083305
2. Flynn, D. F. B., M. M. Gilmore, and E. A. Sudderth. Estimating Traffic Crash Counts Using Crowdsourced Data: Pilot analysis of 2017 Waze data and Police Accident Reports in Maryland. November 2018. Report Number : DOT-VNTSC-BTS-19-01 https://rosap.ntl.bts.gov/view/dot/37256