Abstract: This paper applied singular value decomposition to predict the missing data. An enhanced Pearson correlation coefficient algorithm based on parameter was introduced to increase the accuracy when computing the similarity of user and items. Finally, a new algorithm called "HybridSVD" was explored, which was based on singular value decomposition and our novel similarity model. In the experiment section, the authors evaluated this new algorithm using the dataset MoiveLens and the results suggest that the new algorithm can better handle this matrix sparsity problem.

Key words: collaboration filtering, matrix sparesity, ingular Value Decomposition (SVD), Enhanced Pearson Correlation Coefficient (EPCC)

摘要： 应用奇异值算法得到一个无缺失的矩阵，引进了一种增强的、基于参数的Pearson相关系统算法来提高相关性算法的准确性。提出一个基于奇异值分解和增强Pearson系数的“HybridSVD”算法，用MovieLens数据集来评价该算法，并和其他经典的传统算法做了比较。实验结果证明，“HybridSVD”算法比其他传统算法能更好地处理协同过滤中的稀疏性问题。

关键词: 协同过滤, 矩阵稀疏性, 奇异值分解, 增强的Pearson相关系数