Using Decision Tree Data Mining Algorithm to Predict Causes of Road Traffic Accidents, its Prone Locations and Time along Kano –Wudil Highway

Abstract

Road traffic accidents, the inadvertent crash involving at least one motor vehicle, occurring on a road open to public circulation, in which at least one person is injured or killed; intentional acts (murder, suicide) and natural disasters excluded, is indisputably one of the most frequent and most damaging calamities bedeviling human societies, in particular, Nigeria, today. It is therefore, of paramount importance to seek to identify the root causes of road traffic accidents in order to proffer mitigating solutions to address the menace. This research, aimed at predicting the likely causes of road accidents, its prone locations and time along Kano– Wudil highway in order to take all necessary counter measures is a step forward in this direction. In this study data mining decision tree algorithm was used to predict the causes of the accidents, its prone locations and time along Kano – Wudil Highway that links Kano State to Wudil Local Government Area Kano State for effective decision making. performance were analyzed using road accidents data set. The location is between the first 40 kilometers along the Ibadan-Lagos Express road. The work used Multilayer Perceptron as well as Radial Basis Function (RBF) Neural Networks, Id3 and Function Tree algorithms. that the tree algorithm performed with accuracy performed