改进的基于相关相似性的协同过滤推荐算法

An adaptive algorithm of collaborative filtering recommender based on correlation similarity

分析了传统CF算法和基于项目评分的CF算法中存在的问题,对其相似性计算和推荐集选取方法进行了改进,并提出了一种优化的CF算法。实验结果表明,该算法同传统CF算法相比能显著提高推荐精度,同基于项目评分的CF算法相比能够有效减少计算复杂度。

On the basis of analysing the deficiencies in the traditional CF algorithm and the collaborative filtering recommendation algorithm based on item rating, some improvements on the similarity calculation and recommendation selection were made and an optimized CF algorithm is given. Experimental results show that this method can noticeably provide better recommendation results than traditional CF algorithms, and can efficiently reduce the complexity of computation compared with the CF recommendation algorithm based on item rating.