Using claims prediction model for road safety evaluation

Road safety analysis is typically undertaken using traffic collision data. However, the collision data often suffer from quality and reliability probl ems. These problems can inhibit the ability of road safety engineers to eva luate and analyze road safety performance. An alternate source of data that characterize the events of a traffic collision is the records that become available from an auto insurance claim. In settling an auto insurance claim , a claim adjuster must make an assessment and determination of the circums tances of the event, recording important contributing factors that led to t he crash occurrence. As such, there is an opportunity to access and use the claims data in road safety engineering analysis. This paper presents the r esults of an initial attempt to use auto insurance claims records in road s afety evaluation by developing and applying a claim prediction model. The p rediction model will provide an estimate of the number of auto insurance cl aims that can be expected at signalized intersections in the Vancouver area of British Columbia, Canada. A discussion of the usefulness and applicatio n of the claim prediction model will be provided together with a recommenda tion on how the claims data could be utilized in the future.