Matrix Factorization Recommendation Algorithm Based on User Characteristics
Hongtao Liu, Ouyang Mao, Chen Long, Xueyan Liu, Zhenjia Zhu · 2018
Matrix Factorization is a popular and successful method. It is already a common model method for collaborative filtering in recommendation systems. As most of the scoring matrix is sparse and the dimensions are increasing rapidly, the prediction accuracy and calculation time of the current matrix decomposition are limited. In this paper, a matrix decomposition model based on user characteristics is proposed, which can effectively improve the accuracy of predictive scoring and reduce the number of iterations. By testing the actual data and comparing it with the existing recommendation algorithm, the experimental results show that the method proposed in this paper can predict user's score well.