Improved approaches to mine rare association rules in transactional databases
Rage Uday Kiran, P. Krishna Reddy · 2010
Rare association rules are the association rules consisting of rare items. It is difficult to mine rare association rules with the single minimum support based approaches such as Apri-ori and FP-growth as they suffer from rare item problem. In the literature, efforts has been made to extract rare association rules with multiple minimum supports. It was observed that the multiple minimum supports-based approach still suffers from performance problems. As a part of proposed work, we have analyzed the multiple minimum supports-based approach and proposed improved approaches for extracting rare association rules. Experimental results show that the proposed approaches are efficient.