Crash Frequency Analysis

Abstract

Modeling highway traffic crash frequency is an important approach for identifying high crash risk areas that can help transportation agencies allocate limited resources more efficiently, and find preventive measures. This paper applies a Poisson regression model, Negative Binomial regres-sion model and then proposes an Artificial Neural Network model to analyze the 2008-2012 crash data for the Interstate I-90 in the State of Minnesota in the US. By comparing the prediction per-formance between these three models, this study demonstrates that the Neural Network is an ef-fective alternative method for predicting highway crash frequency.