Effective Matrix Factorization for Recommendation with Local Differential Privacy

With the continuous upgrading of smart devices, people are using smartphones more and more frequently. People not only browse the information they need on the Internet, but also more and more people get daily necessities through online shopping. Faced with a variety of recommendation systems, it becomes more and more difficult for people to keep their privacy from being collected while using them. Therefore, ensuring the privacy security of users when they use the recommendation system is increasingly becoming the focus of people. This paper summarizes the related technologies. A recommendation algorithm based on collaborative filtering, matrix factorization as well as the randomized response is proposed, which satisfies local differential privacy (LDP). Besides, this paper also discusses the key technologies used in privacy protection in the recommendation system. Besides, This paper includes the algorithm flow of the recommendation system. Finally, the experiment proves that our algorithm has higher accuracy while guaranteeing user privacy.