LAUSR

Due to the concise design concept and the superior computing performance, collaborative filtering algorithm has become a hot research field in recommendation systems. Firstly, this paper summarizes the relevant research achievements of collaborative filtering algorithms in recent years. By analyzing data sparsity and scalability problem in collaborative filtering algorithm, a novel collaborative filtering algorithm based on correlation coefficient (COR based) is proposed. The key functional parts of COR-based CF algorithm are the calculation of semantic similarity and the acquirement of similarity–term frequency weight. The main performance metric of COR-based CF algorithm includes means absolute error and hit ratio. The experimental results demonstrate that the COR-based CF algorithm outperforms the traditional collaborative filtering algorithms which are user-based CF algorithm and item-based CF algorithm. In the proposed COR-based CF algorithm, the sparsity and scalability problems among collaborative filtering algorithms have been effectively relieved.