Research on recommendation algorithm based on unified model with explicit and latent factors
Fang Wang · 2014
Recommendation algorithm is one of the major approa ches to solve the information overload problem. The core task is to model and predict users’ preference. The algorithms based on the latent factor model have b een made a great success recently. However, data sparseness co uld lead to the incompleteness of the factors in th is completely data-driven modeling. To address this issue, this p aper leverages certain knowledge of the influencing factors on user preferences to optimize the structure of laten t factor model. This paper proposes a unified model with both explicit factors and latent factors. User demograph ic features and item content features are used as t he clues reflecting users’ preferences. These features are ito the framework of latent factor model i n the form of explicit factors. Experiments on MovieLens dataset suggest that the proposed method is feasible and ef fective.