FCM-type Cluster Validation in Fuzzy Co-Clustering and Collaborative Filtering Applicability
نویسندگان
چکیده
FCM-type cluster validation is a technique for searching for the optimal fuzzy partition, in which the number of clusters is evaluated by considering the degree of overlapping of fuzzy memberships, cluster compactness or cluster separation. In this paper, a new approach for FCM-type cluster validation in fuzzy co-clustering is proposed. Because fuzzy co-clustering does not use cluster prototypes, cluster separation is evaluated without using the distances between cluster prototypes. In numerical experiment, the applicability of the new validity measure to collaborative filtering task is studied using a purchase history data.
منابع مشابه
Exclusive Partition in FCM-type Co-clustering and Its Application to Collaborative Filtering
The task of collaborative filtering has close relation to coclustering, in which personalized recommendation is achieved by connecting users with items to be preferred. FCM-type coclustering extracts user-item co-clusters, in which users are assigned to clusters in an exclusive manner while item partitions are not necessarily exclusive and each item can be shared (rejected) by multiple (all) cl...
متن کاملPartially Horizontal Collaborative Fuzzy C-Means
Horizontal collaborative clustering is such a clustering method that carries clustering on one data set describing a pattern set in one feature space with collaborative introducing of outer partition information obtained by clustering on another data set but describing the same pattern set in another feature space. In order to implement the collaborative clustering, horizontal collaborative fuz...
متن کاملFuzzy Co-Clustering and Application to Collaborative Filtering
Cooccurrence information analysis became more popular in many web-based system analyses such as document analysis or purchase history analysis. Rather than the conventional multivariate observations, each object is characterized by its cooccurrence degrees with various items, and the goal is often to extract co-cluster structures among objects and items, such that mutually familiar object-item ...
متن کاملFuzzy Cluster Validation Based on Fuzzy PCA- Guided Procedure
Cluster validation is an important issue in fuzzy clustering research and many validity measures, most of which are motivated by intuitive justification considering geometrical features, have been developed. This paper proposes a new validation approach, which evaluates the validity degree of cluster partitions from the view point of the optimality of objective functions in FCM-type clustering....
متن کاملFuzzy Cluster Validation Based on Fuzzy PCA- Guided Procedure
Cluster validation is an important issue in fuzzy clustering research and many validity measures, most of which are motivated by intuitive justification considering geometrical features, have been developed. This paper proposes a new validation approach, which evaluates the validity degree of cluster partitions from the view point of the optimality of objective functions in FCM-type clustering....
متن کامل