基于非负矩阵分解的Slope One算法  

Slope One algorithm based on nonnegative matrix factorization

作　　者：董立岩[1,2] 金佳欢 方塬程 王越群[1] 李永丽 孙铭会[1,2] DONG Li-yan;JIN Jia-huan;FANG Yuan-cheng;WANG Yue-qun;LI Yong-li;SUN Ming-hui(College of Computer Science and Technology,Jilin University,Changchun 130012,China;Key Laboratory of SymbolicComputation and Knowledge Engineering of Ministry of Education,Jilin University,Changchun 130012,China;School of Information Science and Technology,Northeast Normal University,Changchun 130117,China)

机构地区：[1]吉林大学计算机科学与技术学院,吉林长春130012 [2]吉林大学符号计算与知识工程教育部重点实验室,吉林长春130012 [3]东北师范大学信息科学与技术学院,吉林长春130117

出　　处：《浙江大学学报（工学版）》2019年第7期1349-1353,1362,共6页Journal of Zhejiang University：Engineering Science

基　　金：国家自然科学基金资助项目(61272209,61872164)

摘　　要：针对协同过滤推荐算法中Slope One算法在稀疏数据集中推荐精度低的问题,利用矩阵分解在解决矩阵稀疏性方面的优势,将非负矩阵分解技术引入到用户-项目评分矩阵的降维处理中,将原有的稀疏评分矩阵进行非负分解,改善了矩阵的稀疏性,优化Slope One算法.从实验数据可以看出,与原始的CF算法进行比较,NMF-Slope One算法有较好的推荐效果.在数据稀疏的条件下,确定参数进行实验.实验结果表明,该方法提高了SlopeOne算法在数据稀疏下的精度和推荐质量.The good performance of matrix decomposition in solving matrix sparsity was used in order to solve the problem that the Slope One algorithm has low recommendation accuracy in the sparse data set in the collaborative filtering recommendation algorithm.The nonnegative matrix factorization technology was introduced into the dimension reduction of the user-item rating matrix in order to optimize the Slope One algorithm.The original sparse scoring matrix was non-negatively decomposed in order to improve the sparsity of the matrix.The experimental results show that the NMF-Slope One algorithm has a good recommendation effect compared with the original CF algorithm.Parameters were determined for experimentation under conditions of sparse data.The proposed method improves the accuracy and the recommendation quality of the Slope One algorithm under data sparseness.

关 键 词：推荐系统 协同过滤 非负矩阵分解 SlopeOne 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]