A multi-objective evolutionary approach for mining frequent and high utility itemsets

Mining interesting itemsets with both high support and utility values from transactional database is an important task in data mining. In this paper, we consider the two measures support and utility in a unified framework from a multi-objective view. Specifically, the task of mining frequent and high utility itemsets is modeled as a multi-objective problem. Then, a multi-objective itemset mining algorithm is proposed for solving the transformed problem, which can provide multiple itemsets recommendation for decision-makers in only one run. One key advantage of the proposed multi-objective algorithm is that it does not need to specify the prior parameters such as minimal support threshold min_sup and minimal utility threshold min_uti, which brings much convenience to users. The experimental results on several real datasets demonstrate the effectiveness of the proposed algorithm. In addition, comparison results show that the proposed algorithm can provide more diverse yet frequent and high utility itemsets in only one run.