基于SQL的不产生候选集的频繁模式挖掘

SQL-based Frequent Pattern Mining Without Candidacy Generation

频繁模式挖掘是数据库挖掘中的一个十分重要的组成部分 ,然而以前的许多研究都是基于Apriori的产生候选集的测试迭代方法。这些方法普遍存在需要多次扫描数据库 ,对产生的大量候选集进行迭代测试的缺陷 ,尤其是对于挖掘长模式时这种缺陷就尤为突出。FP growth方法采用分而治之的策略 ,只需对数据库进行二次扫描 ,而且避免了产生大量候选集的问题。文中的基于SQL的频繁模式挖掘方法既是在此基础上提出的 ,采用子查询及DBMS扩展技术 (如用户定义函数等 )对该方法进行了改进。

A fundamental component in data mining tasks is finding frequent patterns in a given dataset. Most of the previous studies adopt an Apriori-like candidate set generation-and-test approach. However,candidate set is still costly,especially when there aret prolific patterns and/or long patterns. This paper presents an evaluation of SQL based frequent pattern mining with a novel frequent pattern growth (FP-growth) method,which is efficient and scalable for mining both long and short patterns without candidate generation. This paper examines some techniques to improve performance by using DBMS extension and makes performance evaluation on commercial RDBMS (IBM DB2 UDB EEE V8).