Machine Learning Approach to Predict Traffic Accident Occurrence in Bangladesh

Abstract

At present day, fatal road accidents have become a very common fact all over the world and also in Bangladesh. It is increasing day by day in big cities like Dhaka. Thousands of lives are taken every year due to traffic accidents. In this research paper, we have tried to justify the cause behind fatal traffic accidents. By taking several causes as attributes such as the age of driver behind the wheel, experience, vehicle types, health issues of the driver, and so on. Using these causes as the main input criteria we took data records from various fatal accident cases and also non-fatal accident cases through news sources and surveys. In consideration of our research, we applied machine learning algorithms like Decision trees, Random Forest Classifier which justifies our proposed model accuracy. Through the data mining technique, we have got a satisfactory percentage of accuracy of about 95% for Decision Tree Classifier and 93% for Random Forest Classifier.