Utilization of Various Dimensionality Reduction Methods in Collaborative Filtering Based on Rough C-Means Clustering

Abstract

Collaborative filtering (CF) is a technique for realizing recommender systems found in e-commerce sites and video streaming services. Clustering is a technique for automatically classifying and summarizing the data by extracting clusters composed of similar objects. Clustering-based CF extracts clusters composed of users with similar interests and preferences, and recommends contents with high preference degree within the cluster. Collaborative filtering based on rough C-means clustering (RCM-CF) has been proposed as collaborative filtering utilizing rough clustering, and its effectiveness has been reported. In general, there is a problem that the size of data in collaborative filtering is very large and the calculation cost is very high. In this study, we propose collaborative filtering based on rough C-means clustering with various dimensionality reduction methods in order to reduce the calculation cost and verify its effectiveness through numerical experiments.