E-fwarm: Enhanced Fuzzy-based Weighted Association Rule Mining Algorithm

In the Association Rule Mining (ARM) approach, equal weight is assigned to all itemsets in the dataset. Hence, it is not appropriate for all datasets. The weight should be assigned based on the significance of each itemset. The WARM reduces extra steps during the generation of rules. As, the Weighted ARM (WARM) uses the significance of each itemset, it is applied in the data mining. The Fuzzy-based WARM satisfies the downward closure property and prunes the insignificant rules by assigning the weight to the itemset. This reduces the computation time and execution time. This paper presents an Enhanced Fuzzy-based Weighted Association Rule Mining (E-FWARM) algorithm for efficient mining of the frequent itemsets. The prefiltering method is applied to the input dataset to remove the item having low variance. Data discretization is performed and E-FWARM is applied for mining the frequent itemsets. The experimental results show that the proposed E-FWARM algorithm yields maximum frequent items, association rules, accuracy and minimum execution time than the existing algorithms.