Analysis of the Causes of Traffic Accidents and Identification of Accident-Prone Points in Long Downhill Tunnel of Mountain Expressways Based on Data Mining

China has a large vehicle base, uneven road conditions, and the highest rate of traffic accidents in world. Particularly on long downhill sections expressway tunnels mountainous areas with harsh geographical are densely distributed, once accident occurs, consequences serious, which poses threat to people’s lives property. This paper mined analyzed data collected by project Baoding section Zhangshi Expressway. SPSS software was used analyze characteristics tunnel mountain expressways. The time, space, form, type, alignment distribution expressways were obtained. decision tree algorithm construct cause analysis model expressways, five primary influencing factors obtained: horizontal curve radius, week, slope length, cart ratio. improved cumulative frequency method study accident-prone points potential