A Method Mining Correlation High Utility Itemsets with Negative Profits

Abstract

High-utility itemset (HUI) mining is an important task in the data mining process. Recently, many algorithms have been proposed to mine sets of HUIs. Most algorithms only work with data sets with positive return values. However, in the real world, the set of business items often includes both positive (+) and negative (-) profit values. To solve this problem, an algorithm is needed to find HUIs with negative returns in the database.The issue is how to mine efficiently correlation high utility itemsets with negative profits. Given the transactional database D and the profit table of products, how to find the best correlation high utility itemsets on the database with items having negative profits. To address these issues, the paper proposes a COHUIs_CoHUN method to mine correlation high utility itemsets with negative profits