关键词: 数据挖掘, 频繁闭项集, 压缩频繁模式树, 划分矩阵

Abstract: Mining frequent closed itemsets is a fundamental and important issue in many data mining applications. A new depth-first search algorithm for mining frequent closed itemsets called depth-first search for frequent closed itemsets (DFFCI) was proposed, which could reduce the number of candidate itemsets and the cost of support counting. DFFCI projected the dataset information stored by the improved Compressed Frequent Pattern tree (CFP-Tree) into the partition matrix, and improved the efficiency of support counting by using binary vector logic operation. Global 2-itemset pruning based on support pre-counting and local extension pruning were used to prune the search space effectively. The experimental results show that DFFCI outperforms other depth-first search algorithms.

Key words: data mining, frequent closed itemset, Compressed Frequent Pattern Tree (CFP-Tree), partition matrix