A TIFF-tree based High Utility Itemset Mining Algorithm

摘要：

　　Owing to their major contribution to the total transactions sales profits,increasingly importance has been attached to high utility itemsets mining.This paper has proposed a TIFF-tree based algorithm,which takes two-pass database scan to obtain the transaction utility information,the conditional matrix of potential high utility is adopted,through the row-column operation,the calculation of transaction utility can be simplified.The experiment result analysis shows that as the decreasing of user-defined threshold,the performance of TIFP-Growth algorithm is much better than the two-phase algorithm.

关键词： Frequent Pattern Mining Conditional Matrix High Utility Itemsets

作者: Yi Pan Bo Zhang

作者单位: Department of Computer Sci.& Tech,Changsha University,Changsha,412003,China Logistic Engineering School,Wuhan University of Technolog,Wuhan,430074,China

会议类型: 国际会议

会议名称: 2013 2nd international Conference on Opto-Electronics Engineering and Materials Eesearch(2013第二届光电工程与材料研究国际会议)(OEMR2013)

会议地点: 郑州

会议语种:英文

页码: 501-505

在线出版日期: 2013-10-19（万方平台首次上网日期，不代表论文的发表时间）