一种有效且无冗余的快速关联规则挖掘算法

被引：9

作者：

刘乃丽

李玉忱

马磊

机构：

[1] 山东大学计算机科学与技术学院

[2] 山东大学计算机科学与技术学院山东济南

[3] 山东济南

来源：

计算机应用 | 2005年 / 06期

关键词：

关联规则; 频繁项集; 相关度; 冗余性;

D O I：

暂无

中图分类号：

TP311.13 [];

学科分类号：

1201 ;

摘要：

关联规则的挖掘是数据挖掘的一个重要研究领域。传统算法进行关联规则挖掘时,或者生成规则的效率很低,或者生成的关联规则之间存在着大量的冗余,或者挖掘出的规则的支持度和置信度都很高,但却是无趣的、甚至是虚假的规则,且不能产生带有否定项的规则。提出了一种新的算法MVNR(MiningValidandnon RedundantAssociationRulesAlgorithm),利用频繁项集的极小子集集合很好的解决了上述问题。

引用

页码：1396 / 1397+1404 +1404

页数：3

共 12 条

[1]

BeyondMarketBaskets:Generalizing Association Rules to Correlations. BR IN S,MOTWANIR,SILVERSTEIN C. In Proc1997 ACM-SIGMOD Int ConfManagement of Data (SIGMOD 97 )[C] . 1997

[2]

Finding interesting rules from large sets of discovered association rules. KLEMETTINEN M,MANNILA H,RONKAINEN P,et al. In 3 rd Intl. Conf Information and Knowledge Management[C] . 1994

[3]

M ining the most interesting rules. BAYARDO RJ,AGRAWAL R. In 5 th ACM SIGKDD Intl Conf on Knowledge D iscovery and DataM ining . 1999

[4]

M ining M inimal Non-redundant Association Rules Using Frequent C losed Itemsets. BASTIDE Y,PASQUIER N,TAOUIL R,et al. Proceedings of the First International Conference on Computational Logic . 2000

[5]

Generating non-redundant association rules. ZAKIMJ. Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data m ining . 2000

[6]

CHARM: An efficient algorithm for closed association rule m ining. ZAKIMJ,HSIAO C -J. Technical Report 99 - 10, Computer Science Dept, Rensselaer Polytechnic Institute . 1999

[7]

E fficientm ining of association rules using closed itemset lattices. PASQUIER N,BASTIDE Y,TAOUIL R,et al. Information Systems, 24 (1 ): 25 -46 . 1999

[8]

A new approach to online generation of Association Rules. Aggarwal C C,Yu P S. IEEE Transactions on Knowledge and Data Engineering . 2001

[9]

Online Generation ofProfile Association Rules. AGGARWAL CC,SUN Z,YU PS. Proc KDD Conf . 1998

[10]

FastA lgorithms forM ining Association Rules in Large Databases. AGRAWAL R,STR IKANT R. In Research ReportRJ 9839, IBM A lmaden Research Center . 1994

← 1 2 →