Mining of frequent itemsets with JoinFI-mine algorithm

Abstract

Association rule mining among frequent items has been widely studied in data mining field. Many researches have improved the algorithm for generation of all the frequent itemsets. In this paper, we proposed a new algorithm to mine all frequents itemsets from a transaction database. The main features of this paper are: (1) the database is scanned only one time to mine frequent itemsets; (2) the new algorithm called the JoinFI-Mine algorithm which use mathematics properties to reduces huge of subsequence mining; (3) the proposed algorithm mines frequent itemsets without generation of candidate sets; and (4) when the minimum support threshold is changed, the database is not require to scan. We have provided definitions, algorithms, examples, theorem, and correctness proving of the algorithm.