Paper Title
Classification of Traffic Accident Prediction Models: A Review Paper

Abstract
Accident prediction models (APMs) are extremely important tools for estimating the expected number of accidents on entities such as intersections and street segments. These estimates are typically used in the identification of sites for possible safety treatment and in the evaluation of such treatments. An APM is, in principally, a mathematical equation that expresses the average accident frequency of a site as a function of traffic flow and other site characteristics. whilst, the credibility of an APM is enhanced if the APM based on data as many years as possible especially if data for those same years are utilized in the safety analysis of a site. This paper covered a review as many papers as possible and various gaps in research along with a future possibility of study in this area have been indicated. Several models were discussed in this paper such as multiple linear regressions, Poisson regression, Conway-Maxwell Poisson regression models, artificial neural networks and fuzzy logics. Index Terms - Traffic Accidents Prediction, Multiple Linear Regression, Poisson Regression, Literature Review, Artificial Neural Networks.