摘要
为了解决关联规则挖掘过程中会生成大量关联规则的问题,提出了一种基于集合枚举树的挖掘关联规则的改进算法.此算法在不丢失任何信息的情况下只生成关联规则的某些前件集,大大减少了关联规则的生成数量,提高了用户分析关联规则结果的效率.
To solve the problem that a lot of association rules may be generated in the process of association rules mining, an improved algorithm based on the set-enumeration tree for mining the association rules is presented, and the algorithm reduces the number of association rules remarkably and generates some subset of the association rules while any information may not be lost. The efficiency of the analysis for the association rules will be enhanced.
出处
《郑州轻工业学院学报（自然科学版）》
CAS
2008年第3期117-120,共4页
Journal of Zhengzhou University of Light Industry:Natural Science
基金
国家自然科学基金项目(60474022)
河南省高校杰出科研人才创新工程项目(2007KYCX018)
关键词
频繁项集
关联规则
集合枚举树
frequent itemset
association rule
set-eumeration
