期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2015
卷号：6
期号：6
页码：5261-5264
出版社：TechScience Publications
摘要：High utility item sets (HUIs) mining is an emanate topic in data mining, which refers to discovering all item sets having a utility meeting a user-specified minimum utility threshold. We used three efficient algorithm ApriorCH (Apriori-based algorithm for mining High utility closed itemset), Apriori HC-D (AprioriHC algorithm with removing unpromising and isolated items) and CHUD (Closed High Utility itemset Discovery) algorithm. However, setting min_util appropriately is a hard problem for users. Finding an appropriate minimum utility threshold by trial and error is a tough process for users. Setting very low min_util, HUIs will be generated in large, which may cause the mining process to be very inefficient. In another way, by setting too high min_util, no HUI will be found. So the above issues is addressed by proposing a framework for mining top-k high utility item set , where k is the desired number of HUIs to be mined. Two types of proficient algorithms named TKU (mining Top-K Utility item sets) and TKO (mining Top-K utility item sets in one phase) are proposed for mining such item sets without the need to set min_util.
关键词：Utility Mining; Data Mining; High Utility Item;Set; Closed High Utility Item Set; Minimum Utility Threshold;Top-K High Utility Item Set; Lossless and Concise;representation.
