Addressing the cold start problem in privacy preserving content-based recommender systems using hypercube graphs

The initial interaction of a user with a recommender system is problematic because, in such a so-called cold start situation, the recommender system has very little information about the user, if any. Moreover, in collaborative filtering, users need to share their preferences with the service provider by rating items while in content-based filtering there is no need for such information sharing. A content-based model using hypercube graphs has recently been proposed and appears to be able to estimate user profiles based on a very limited number of ratings while preserving user privacy. In this paper, we confirm these findings on the basis of experiments with more than 1000 users in the restaurant and movie domains. We show that the proposed method outperforms standard machine learning algorithms when the number of available ratings is at most 10, which often happens, and is competitive with larger training sets. In addition, training is simple and doesn’t require large computational efforts.