Prediction of Traffic Accident Severity Based on Random Forest

This paper used the data of automobile traffic accidents from 2018 to 2020 in Chinese National Automobile Accident In-Depth Investigation System. The prediction features accident severity are innovated. Four that did not participate importance ranking were added: location, form, road information, and collision speed. Eight (engine capacity, hour day, age vehicle, month year, day week, band drivers, vehicle maneuver, speed limit) have been previous studies. Random forest was rank 12 features, 7 important finally adopted. By comparing algorithms optimizing results, model degree with higher accuracy is obtained.