摘要
关联规则挖掘是数据挖掘研究中的一个重要方面,而其中一个重要问题是对挖掘出的规则的感兴趣程度的评估。实际应用中可从数据源中挖掘出大量的规则,但这些规则中的大部分对用户来说是不一定感兴趣的。关联规则挖掘中的有趣性问题可从客观和主观两个方面对关联规则的兴趣度进行评测。利用模板将用户感兴趣的规则和不感兴趣的规则区分开,以此来完成关联规则有趣性的主观评测;在关联规则的置信度和支持度基础上对关联规则的有趣性的客观评测增加了约束。
Mining the association rules is an important aspect of the study of data mining,and one of the important problems is the evaluation of interestingness of the discovered rules.In many real-life applications it is easy to generate a large number of rules from databases.But most of them are not useful or interesting to the user.In order to find the useful association rules,the interestingness of mining association rules is discussed.There are two approaches for evalua-tion of interestingness,objective measure and subjective measure.For subjective measure,Templates are used to differenti-ate the rules interested to the users or not.For objective measure the interestingness of association rules is first defined on the basis of the support and confidence of association rules and the interestingness of association rules is then eval-uated accordingly.
出处
《计算机工程与应用》
CSCD
北大核心
2003年第6期190-192,共3页
Computer Engineering and Applications
