The Recommendation system relies on feedback and personal information collected from users for effective recommendation. The success of a recommendation system is highly dependent on storing and managing sensitive customer information. Users refrain from using the application if there is a threat to user privacy. Several works that were performed to protect user privacy have paid little attention to utility. Hence, there is a need for a robust recommendation system with high accuracy and privacy. Model-based approaches are more prevalent and commonly used in recommendation. The proposed work improvises the existing private model-based collaborative filtering algorithm with high privacy and utility. We identified that data sparsity is the primary reason for most of the threats in a recommender framework through an extensive literature survey. Hence, our approach combines the l injection for imputing the missing ratings, which are deemed low, with differential privacy. We additionally introduce a random differential privacy approach to alternating least square (ALS) for improved utility. Experimental results on benchmarked datasets confirm that the performance of our private noisy Random ALS algorithm outperforms the non-noisy ALS for all datasets.
Keywords: alternating least square; data sparsity; differential privacy; l injection, matrix factorization; recommendation system; unbounded differential privacy.