FHN: Efficient Mining of High-Utility Itemsets with Negative Unit Profits

High utility itemset (HUI) mining is a popular data mining task. It consists of discovering sets of items generating high profit in a transaction database. Several efficient algorithms have been proposed for this task. But few can handle items with negative unit profits despite that such items occurs in many real-life transaction databases. Mining HUIs in a database where items have positive and negative unit profits is a very computationally expensive task. To address this issue, we present an efficient algorithm named FHN (Faster High-Utility itemset miner with Negative unit profits). FHN discovers HUIs without generating candidates and introduces several strategies to handle items with negative unit profits efficiently. Experimental results with six real-life datasets shows that FHN is up to 500 times faster and can use up to 250 times less memory than the state-of-the-art algorithm HUINIV-Mine.