A NMF-Based Privacy-Preserving Recommendation Algorithm
Tao Li, Chao Gao, Jinglin Du · 2009
The users pay more and more attention to personal information security with the recommender system applied widely. In this paper, a privacy-preserving collaborative filtering algorithm based on non-negative matrix factorization (NMF) is presented, which is combined with random perturbation techniques. The experimental results show that the algorithm cannot only protect users' privacy, but also generate recommendations with decent accuracy.