1M.E Student, Dept ofIT,Kongu Engineering College,Perundurai,Erode.
2Assistant Prfessor, Dept of IT, Kongu Engineering College,Perundurai,Erode.
The attention of the research community has been focused on the infrequent itemset mining problem.i.e., discovering itemsets whose frequency of occurrence in the analyzed data is less than or equal to a maximum threshold.Infrequent itemset discovery is applicable to data coming from different real-life application contexts such as (i) statistical disclosure risk assessment from census data(ii) online shopping and (iii) fraud detection.Frequent weighted …show more content…
The first attempt to perform itemset mining was focused on discovering frequent itemsets, i.e., patterns whose observed frequency of occurrence in the source data (the support) is above a given threshold. Frequent itemsets find application in a number of real-life contexts (e.g., market basket analysis ,medical image processing , biological data analysis ).Many traditional approaches ignore the influence/interest of each item/transaction within the analyzed data. To allow treating items/transactions differently based on their relevance in the frequent itemset mining process, the notion of weighted itemset has also been introduced. A weight is associated with each data item and characterizes its local significance within each transaction. The attention of the research community has also been focused on the infrequent itemset mining problem, i.e., discovering itemsets whose frequency of occurrence in the analyzed data is less than or equal to a maximum threshold. The traditional infrequent itemset mining algorithms still suffer from their inability to take local item interestingness into account during the mining phase. In fact, on the one hand, itemset quality measures used to drive the frequent weighted itemset mining process are not directly applicable to accomplish the infrequent weighted itemset mining task …show more content…
The goal is to steer the mining focus to those significant relationships involving items with significant weights rather than being flooded in the combinatorial explosion of insignificant relationships. The limitation of the traditional Association Rule Mining models in particular, its incapacity for treating units differently. The weight can be integrated in the mining process to solve this problem. It identifies the challenge faced when making improvement towards using weight, in particular the invalidation of downward closure property. A set of new concepts are proposed to adapt weighting in the new setting. Among them is the proposal of using “weighted downward closure property” as a replacement of the original “downward closure property”. This is proved as valid and justifies the effective mining strategy in the new framework of “weighted support –