Comparison of random forest and support vector machine regression models for forecasting road accidents
Gatera Antoine, Martin Kuradusenge, Gaurav Bajpai, Chomora Mikeka, Sarika Shrivastava
Abstract
One of the world’s concerns today is the rate of road traffic accidents (RTA). The overwhelming majority of these accidents occur in low and middle-income countries. RTA are one of the leading causes of death in Rwanda. RTA prediction is crucial for both transportation management and intelligent transportation systems (ITS) development. This paper adopted the use of two modelling techniques, Random forest (RF) and Support vector machine (SVM) for short-term road accident forecasting. The data used to evaluate the models was obtained from the Police. The lower error indices of MAE, MSE, RMSE and higher coefficient of determination (R2) were accuracy measures in comparing the models. The RF model performed better than the SVM model as it revealed higher R2=0.91 compared to the SVM model that was with R2=0.86. Machine learning methods are promising tools for the prediction of road accidents. Prediction positively influences safety enhancements and regulation formulation to prevent future accidents. The appropriate prediction method would help policymakers and healthcare providers adjust their contributions to the accident management process.