Efficient closed high-utility itemset mining
Philippe Fournier‐Viger, Souleymane Zida, Jerry Chun‐Wei Lin, Chengwei Wu, Vincent S. M. Tseng · 2016
This paper presents a novel algorithm for discovering closed high-utility itemsets (CHUIs) efficiently. It proposes three strategies to mine CHUIs efficiently: closure jumping, forward closure checking and backward closure checking. It also relies on two new upper-bounds named local utility and sub-tree utility to prune the search space, and a Fast Utility Counting technique to calculate these upper-bounds efficiently. Moreover, it integrates novel efficient database projection and transaction merging techniques. Experimental results shows that the proposed algorithm is up to 71 times faster and consumes up to 18 times less memory than the state-of-art CHUD algorithm.