TRAFFIC SAFETY: C.R.A.S.H. helping Tenn. Highway Patrol predict traffic accidents

New software analyzes likely crash factors to determine likelihood of an incident

August 04, 2014

For the last six months, the Tennessee Highway Patrol has been making use of a new predictive analytics software to better anticipate when and where traffic accidents are likely to occur. While it’s too soon to tell exactly how effective the technology has been, THP reports that traffic fatalities are 5.5% lower now than this time in 2013.

The program, which the department is calling Crash Reduction Analyzing Statistical History, or C.R.A.S.H., looks at the Tennessee road network in segments of 30 square miles; then within those segments, it estimates traffic risks in four-hour increments. THP can program in any number of factors that can impact traffic—from local events to weather patterns and historic crash data—and C.R.A.S.H. will determine which factors are most relevant in a given segment.

At press time, THP noted that C.R.A.S.H. has had an accuracy rate of approximately 72%. Using this information, THP has been able to deploy officers more efficiently, allowing them to either prevent accidents or arrive on-scene more quickly.

Implementing C.R.A.S.H. has cost THP $243,000 to date, with all of the funding coming through federal grants courtesy of the Governors Highway Safety Office.