E-commerce recommendation method based on RBFN and fuzzy art
Huiying Zhang · Jisuanji yingyong yanjiu · 2012
Collaborative filtering algorithm has a less effective recommendation when faced with sparse data,it has cold start,sparsity,scalability and other issues.This paper proposed a recommendation approach using radial basis function network(RBFN) to solve the shortcomings of traditional collaborative filtering.The method smoothened effectively the sparse data,so that sparse matrix became complete.At the same time,the method used the fuzzy art to adaptively cluster similar users,and gave real-time recommendation.Experimental results show that compared with traditional collaborative filtering methods,the proposed method is more effective both in the accuracy or relevance of recommendations.