Machine learning approach on road accidents analysis in Calabarzon, Philippines: an input to road safety management

This research was conducted to help the traffic policy makers and general public in preventing road incidents using collected accident dataset between years 2016 2019. Data mining classification algorithm utilized develop a predictive model for predicting occurrences of accidents. Classification algorithms such as decision tree, k-nn, naïve bayes neural network have been compared identifying better capability classifying stage felony. Neural shows very promising result with total accuracy 87.63%. Nonetheless, k-nn both acquired higher than 80% which that this were also good Moreover, vehicle is more prone rather private felony may occur or on 3:00pm 6:00pm.