CLOLINK: An Adapted Algorithm for Mining Closed Frequent Itemsets

Abstract

Mining of the complete set of frequent itemsets will lead to a huge number of itemsets. Fortunately, this problem can be reduced to the mining of closed frequent itemsets, which results in a much smaller number of itemsets. Methods for efficient mining of closed frequent itemsets have been studied extensively by many researchers using various strategies to prove their efficiencies such as Apriori-likemethods, FP growth algorithms, Tree projection and so on. However, when mining databases, these methods still encounter some performance bottlenecks like processing time, storage space and so on. This paper integrates the advantages of the strategies of H-Mine, a memory efficient algorithmfor mining frequent itemsets. The study proposes an algorithm named CLOLINK, which makes use of a compact data structure named L struct that links the items in the database dynamically during the mining process. An extensive experimental evaluation of the approach on real databases shows a better performance over the previous methods in mining closed frequent itemsets.