A Cluster-Based Similarity Fusion Approach for Scaling-Up Collaborative Filtering Recommender System

Collaborative Filtering (CF) recommenders work by collecting user ratings for items in a given domain and computing similarities between users or items to produce recommendations. The user-item rating database is extremely sparse. This means the number of ratings obtained is very small compared with the number of ratings that need to be predicted. CF suffers from the sparsity problem, resulting in poor quality recommendations and reduced coverage. Further, a CF algorithm needs calculations that are very expensive and grow non-linearly with the number of users and items in a database. Incited by these challenges, we present Cluster-Based Similarity Fusion (CBSF), a new hybrid collaborative filtering algorithm which can deal with the sparsity and scalability issues simultaneously. By the use of carefully selected clusters of users and items, CBSF reduces the computational cost of traditional CF, while retaining high accuracy. Experimental results demonstrate that apart from being scalable, CBSF leads to a better precision and coverage for the recommendation engine.