The folly of using an outcome to predict the future

If we are to reach the Vision Zero goal where no lives are lost on our roads, then a paradigm shift is required in the way we approach many aspects of road safety. This paper examines the predictive robustness of using historic crash to forecast future crash occurrence and compares it to a proactive risk approach. The findings provide compelling evidence that reactive approaches relying on crash history should be a secondary consideration to proactive risk-based approaches in both the identification of high-risk locations and the assessment of interventions.