Integrating Context Similarity with Sparse Linear Recommendation Model

Abstract

Context-aware recommender systems extend traditional recommender systems by adapting their output to users’ specific contextual situations. Most of the existing approaches to context-aware recommendation involve directly incorporating context into standard recommendation algorithms (e.g., collaborative filtering, matrix factorization). In this paper, we highlight the importance of context similarity and make the attempt to incorporate it into context-aware recommender. The underlying assumption behind is that the recommendation lists should be similar if their contextual situations are similar. We integrate context similarity with sparse linear recommendation model to build a similarity-learning model. Our experimental evaluation demonstrates that the proposed model is able to outperform several state-of-the-art context-aware recommendation algorithms for the top-N recommendation task.