Efficient IUA-FP Approach for Utility Pattern Mining

摘要

Traditional methods of association rule mining consider the appearance of an item in a transaction, whether or not it is purchased, as a binary variable. But, the quantity of an item purchased by the customers may be more than one, and the unit cost may not be the same for all items. Utility mining is a generalized form of the share mining model introduced to overcome the mentioned problem. Developing an efficient algorithm is vital for utility mining because high utility itemsets cannot be identified by the pruning strategy. In this paper, an efficient approach is proposed for utility pattern mining with the aid of FP-growth algorithm. The efficiency of utility pattern mining is achieved with incorporating the utility values after mining the frequent patterns (IUA-FP). Here, the patterns that are mined from the FP-growth algorithm are utilized to generate high utility patterns using internal and external utility. Experimentation is carried out on using Retail dataset, a real market basket datasets. The proposed approach generated less number of frequent patterns compared to the FP-growth algorithm in literature and also provided much similar results only for the utility threshold. Hence, the performance study shows that the proposed approach is efficient in mining high utility patterns.