Application of Association Rules Mining to Traffic Accidents Analysis

It is an important measure to find the key factors that cause traffic accidents from a large number of traffic accident data in order to improve safety of road. Based on the traffic accident data of a city in the whole year, the improved Apriori algorithm was used to mine the strong association rules and a new dependence measure-correlation was adopted to further improve the association rules. Then the influence law of each factor on traffic accidents was found out. Experimental results show that the method can improve the efficiency of association rule mining, and quantify the correlation between the cause of the accident and the result of the accident, so as to find out the valuable rules. The study methods and results can provide decision support for relevant traffic management departments.