A Review on Efficient Algorithms for Mining Top-K High Utility Item Sets

High utility itemsets (HUIs) mining is most important topic in data mining.HUI mining means searching all itemsets whose utility is meeting with user-specified minimum utility threshold value i.e min-util. However, Deciding min-util value approximately or exactly is found bit difficult to users, since finding an appropriate minimum utility threshold by trial and error is a tedious as well as time consuming process. Also problem with the same was if threshold value set too low, number of high utility itemset generated were too high,which in turn making the mining process ineffective. Whereas if min-util is set too high, it is likely that very less or no HUIs will be found. The proposed algorithm address the above issues by proposing a new framework for top-k high utility itemset mining, where k is the required number of HUIs to be mined. Two types of efficient algorithms named TKU (mining Top-K Utility itemsets) and TKO (mining Top-K utility itemsets in One phase) are proposed for mining such itemsets without the need to set threshold value by user. System provide comparison of the two algorithms with discussions on their advantages and limitations.