Reducing Redundant Association Rules Using Type-2 Fuzzy Logic

Abstract

Data mining (DM) is an analysis extensive data in order to gain the novel and hidden information. DM is vital to research domains like statistics, artificial intelligence, machine learning, and soft computing. Association Rule Mining (ARM) in enormous databases is a fundamental topic of DM. Discovering frequent itemsets are an underlying process in ARM. Frequent itemsets are employed using statistical measures like Support (Sup) and Confidence (Conf). ARM is practiced to produce association rules (ARs) from frequent itemsets. Such rules reveal a connection between items in the actual world. Numerous algorithms have submitted to attain these rules. However, such algorithms suffer from troubles of redundancy and a sizable count of derived ARs, which renders algorithms inefficient and renders it complicated for end-users to grasp created rules. Due to these motives, this paper adopts the type-2 fuzzy association rules mining technique (T2FARM) to attain frequent items, locate all relationships among items and AR which fulfill minimum support (min sup) and minimum confidence (min conf) values in addition to prune redundant rules in. Empirical evaluations display that the proposed technique improves redundant rules pruning of DM compared to traditional fuzzy association rules (FARs).