Traffic Accident Severity Prediction Using Naive Bayes Algorithm - A Case Study of Semarang Toll Road
Wiwik Budiawan, Singgih Saptadi, Sriyanto Sriyanto, C Tjioe, Tammany Phommachak · IOP Conference Series Materials Science and Engineering · 2019
Abstract A traffic accident was one of the leading cause of death in Indonesia. Toll Road is one of the places where traffic accidents occur. In 2007-2017 there were 501 accidents at Semarang Toll Road. Accident in Semarang Toll Road has a variety of severity. The most severe case is death. A traffic accident can lead to death. One of the ways to decrease the number of the accident was decreased the severity of the accident. This achieved by making a prediction model. The prediction model can predict the severity of the accident based on the attribute affecting the severity of the accident. In this research, Days, Type of Road, Weather, Condition of Road, Time of the accident, Sex of Driver, and Type of Vehicle were chosen as attributes to make prediction model of accident severity. Naive Bayes algorithm was used to make the model which can predict accident severity. The result was an accident prediction model with an accuracy of 39.49% to predict accident severity and the probability of an accident.