Prediction of Road Traffic Accidents in Jordan using Artificial Neural Network (ANN)

Abstract

Highway related accidents are considered one of the most serious problems in the modern world as traffic accidents cause serious threat to human life worldwide. Jordan, a developing country, has high and growing level of traffic accidents resulting in more than 13000 fatalities between 1989 and 2012 with an average annual cost of over $500 million. Prediction of future traffic accidents is therefore of utmost importance in order to appreciate the magnitude of the problem and speed up the decision making towards its alleviation. In this paper, a traffic accident prediction model was developed using the novel Artificial Neural Network (ANN) simulation with the aim of identifying its suitability for prediction of traffic accidents under Jordanian conditions. The results demonstrated that the estimated traffic accidents, based on sufficient data, are close enough to actual traffic accidents and thus are reliable to predict future traffic accidents in Jordan. 