Association Rule Mining for Road Traffic Accident Analysis: A Case Study from UK

摘要

Road Traffic Accidents (RTAs) are currently the leading causes of traffic congestion, human death, health problems, environmental pollution, and economic losses. Investigation of the characteristics and patterns of RTAs is one of the high-priority issues in traffic safety analysis. This paper presents our work on mining RTAs using association rule based methods. A case study is conducted using UK traffic accident data from 2005 to 2017. We performed Apriori algorithm on the data set and then explored the rules with high lift and high support respectively. The results show that RTAs have strong correlation with environmental characteristics, speed limit, and location. With the network visualization, we can explain in details the association rules and obtain more understandable insights into the results. The promising outcomes will undoubtedly reduce traffic accident effectively and assist traffic safety department for decision making.