Conditional restricted Boltzmann machine for item recommendation

Abstract

Recommender systems provide an excellent solution to the issue of information overload by generating item recommendation from a huge collection of items based on users’ preferences. In terms of modeling users’ rating data, existing methods are mainly neighborhood- and factorization-based methods, most of which are rating oriented. Among network-based methods, the restricted Boltzmann machine (RBM) model is also applied to rating prediction tasks. However, item recommendation tasks play a more important role in the real world, due to the large item space as well as users’ limited attention. In this paper, we treat users’ rating behaviors from a new perspective and study the effectiveness of conditional RBM (CRBM) in modeling users’ rating preferences for top-k recommendation. We conduct extensive empirical studies on four real-world datasets and find that our proposed CRBM-IR is very competitive in exploiting users’ explicit rating feedback in comparison with the closely related works.