An effective algorithm for mining association rules based on imperialist competitive algorithm

Association rule mining is one of the most applicable techniques in data mining, which includes two stages. The first is to find the frequent itemsets; the second is to use them to generate association rules. A lot of algorithms have been introduced for discovering these rules. Most of the previous algorithms mine occurrence rules, which are not interesting and readable for the users. In this paper, we propose a new efficient algorithm for exploring high-quality association rules by improving the imperialist competitive algorithm. The proposed method mine interesting and understandable association rules without relying upon the minimum support and the minimum confidence thresholds in only single run. The algorithm is evaluated with several experiments, and the results indicate the efficiency of our method.