A content-based recommendation approach based on singular value decomposition

In the Internet era, where information and communication technologies (ICT) allow data exchange, new tools able to select the correct data are needed. In this field, Recommender Systems have a prime location. The recommendation methods take many forms based on the information exploited in order to provide rating forecasts. However, all of them can choose the correct information to support users. Indeed, these methods allow for overcoming the information overload problem. This paper introduces the theoretical bases of a novel recommendation method defined Rating Singular Value Decomposition (RSVD). RSVD is a Content-Based method that exploits the Singular Value Decomposition properties in order to calculate rating forecasts. This method aims to elaborate the users and items profile to obtain matrices related to ones obtained in Collaborative Filtering methods that exploit Singular Value Decomposition. The accuracy of RSVD is compared with the accuracy of Collaborative Filtering methods, and a study on the sparsity problem is performed. The results obtained are promising.