Accident Severity Prediction Using Data Mining Methods

Abstract

The smart city concept provides opportunities to handle urban problems, and also to improve the citizens’ living environment. In recent years, road traffic accidents (RTAs) have become one of the largest national health issues in the world and it is leading cause for deaths. The burden of road accident casualties and damage is much higher in developing countries than in developed countries. Many factors (driver, environment, vehicle, etc.) are related to traffic accidents, some of those factors are more important in determining the accident severity than others. The analytical data mining solutions can significantly be employed to determine and predict such influential factors among human, vehicle and environmental factors. In this research, the classification technique i.e., Random forest algorithm is used to identify relevant patterns and for classifying the type of accident severity of various traffic accidents with the help of influential environmental features of RTAs that can be used to build the prediction model. This technique was tested using a real dataset. A decision system has been built using the model generated by the Random Forest technique that will help decision makers to enhance the decision making process by predicting the severity of the accident.