Efficient Algorithms for Mining of High Utility Itemsets

--The utility of an itemset represents its importance, which can be measured in terms of weight, value, quantity or other information depending on the user specification. High utility itemsets mining identifies itemsets whose utility satisfies a given threshold. It allows users to quantify the usefulness or preferences of items using different values. Thus, it reflects the impact of different items. High utility itemsets is useful in decision making process of many applications, such as retail marketing and Web service, since items are actually different in many aspects in real applications. One of its popular applications is market basket analysis, which refers to the discovery of sets of items (itemsets) that are frequently purchased together by customers. However, in this application, the traditional model of FIM may discover a large amount of frequent but low revenue itemsets and lose the information on valuable itemsets having low selling frequencies. We propose a novel framework for mining closed+ high utility itemsets (CHUIs), which serves as a compact and lossless representation of HUIs. We propose three efficient algorithms named AprioriCH (Apriori-based algorithm for mining High utility Closed+ itemsets), AprioriHC-FD (AprioriHC algorithm with Fast Discarding unpromising and isolated items) and FCHUD (Fast Closed+ High Utility itemset Discovery) and the integration of closed itemset mining and high utility itemset mining and find possible to develop other compact representations of high utility itemsets inspired by our work to reduce the number of redundant high utility patterns.