摘要
Apriori算法及其改进是目前应用最为广泛的频繁项集挖掘算法,但其在关系数据库中挖掘频繁项集时,产生大量候选项集,导致重复扫描数据库,从而导致其效率低下.本文在深入研究Apriori算法及其改进算法和关系数据库特征的基础上,提出了基于关系数据库的频繁项集挖掘算法,并详细描述了其实现和优化方法.本算法不产生候选项集,只需一次事务扫描,大幅提高算法执行效率,此外,本算法经过简单修改就能满足大部分的关联分析需求.在零售业中的应用实验证明:该算法在一定的条件下比经典的Apriori算法具有更高的效率.
Apriori algorithm and its improvements is the most widely used algorithm for mining frequent itemsets, but 'producing a great quantity of candidate itemsets during min- ing frequent itemsets in relational database, and scans transaction database repeatedly. This paper makes profound researches on Apriori algorithm and the characteristics of relational database, and proposes a frequent itemsets mining algorithm based on relational database, and presents its concrete implementation and its optimization method. The algorithm doesn't produce, candidate itemsets, and only scans transaction database once, so promotes consider- ably efficiency. Moreover, the algorithm meets most requirements of correlation analysis. The result of experiments in the retail industry show that, the frequent itemsets mining algorithm based on relational database' has higher efficiency than the classical Apriori algorithm under certain conditions.
出处
《数学的实践与认识》
CSCD
北大核心
2013年第12期198-203,共6页
Mathematics in Practice and Theory