结合关联规则与FCM的用户聚类改进

Improvement on Users Clustering Combining Association Rules with FCM

结合关联规则与模糊C均值聚类(Fuzzy C-Means,FCM)进行用户聚类,首先将用户访问事务集构造出页面关联矩阵,以此来计算用户浏览路径之间的相似程度,接着利用FCM算法对用户进行聚类.通过与传统聚类比较的实验证明,此方法是有效的且更符合实际.

The paper performs users clustering combining association rules with FCM （Fuzzy C-Means）, firstly it uses the transaction of users＇ accessing to construct the association matrix on pages, and calculates the similarity degree of the user access paths based on that, then it uses the FCM algorithm to perform users clustering. Lastly the experiment that is compared the method which the paper study on with the clustering in tradition shows the algorithm is effective and realistic.