New algorithm for finding frequent and rare itemsets

In this paper, we have proposed two new approaches Per_SPAM and Mis_SPAM. Per_SPAM is the periodic approach to discover frequent patterns in item sequences. Mis_SPAM is the minimum item support approach to extract rare items. The outcome of these approaches is the proposal of a new algorithm called New_SPAM which incorporates periodic and minimum item support approach. The new algorithm assigns minimum item support values for frequent as well as rare items based on their item supports. The performance of proposed algorithm and approaches is compared against frequent sequence count and running time. Experimental results on real-life datasets show that the proposed approaches and new algorithm have better efficiency over the existing algorithm CM_SPAM.