一种基于分类的关联规则研究  

Study of Association Rules Based on Classification Technology

作　　者：王勇[1] 张伟[1] 

机构地区：[1]重庆教育学院计算机与现代教育技术系,重庆400067

出　　处：《计算机科学》2008年第7期170-172,共3页Computer Science

基　　金：中国博士后科学基金一等资助项目(No.20060390175);重庆市教委资助项目(No.kj071502;No.kj051501;No.kj061501);重庆市科委自然科学基金资助项目(No.CSTC;2005BB2286;2006BB2254)

摘　　要：传统的Apriori关联法则算法必须经过大量反复的数据库扫描才能产生候选项集,效率较低。提出一个改进的CBA(Classification Based Apriori)算法。此算法仅需扫描数据库一次,将数据库经过预处理后,再将事务数据库进行分类并保存分类结果,比较时可以不与所有事务记录进行比较,从而减少扫描数据库的次数与比较时间,且又能确保挖掘结果的完整性与正确性。Typical association rules algorithm contais weaknesses such as often requiring a large number of repeated passes over the database to generate the candidate item sets. In this paper,we present an improved method named CBA （Classification Based Apriori）. The CBA method scans the database once. After preprocessing the database, we imploy the classification technology to classify the database and save the results. Thus, the large itemsets are generated by con- trasts with the partial classified transaction records. This not only prunes considerable amounts of data reducing the time needed to perform data scans and requiring less contrast, but also ensures the correctness of the mined results.

关 键 词：数据挖掘 关联法则 分类 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论] TP301.6[自动化与计算机技术—计算机科学与技术]