Elimination of redundant association rules—an efficient linear approach

Abstract

Association rule mining plays an important role in data mining and knowledge discovery. Market basket analysis, medical diagnosis, protein sequence analysis, social media analysis etc., are some prospective research areas of association rule mining. These types of datasets contain huge numbers of features/item sets. Traditional association rule mining algorithms generate lots of rules based on the support and confidence values, many such rules thus generated are redundant. The eminence of the information is affected by the redundant association rules. Therefore, it is essential to eliminate the redundant rules to improve the quality of the results. The proposed algorithm removes redundant association rules to improve the quality of the rules and decreases the size of the rule list. It also reduces memory consumption for further processing of association rules. The experimental results show that, our proposed method effectively removes the redundancy.