Leveraging Image Visual Features in Content-Based Recommender System

Content-based (<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M1"><mml:mrow><mml:mtext>CB</mml:mtext></mml:mrow></mml:math>) and collaborative filtering (<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M2"><mml:mrow><mml:mtext>CF</mml:mtext></mml:mrow></mml:math>) recommendation algorithms are widely used in modern e-commerce recommender systems (<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M3"><mml:mrow><mml:mtext>RSs</mml:mtext></mml:mrow></mml:math>) to improve user experience of personalized services. Item content features and user-item rating data are primarily used to train the recommendation model. However, sparse data would lead such systems unreliable. To solve the data sparsity problem, we consider that more latent information would be imported to catch users’ potential preferences. Therefore, hybrid features which include all kinds of item features are used to excavate users’ interests. In particular, we find that the image visual features can catch more potential preferences of users. In this paper, we leverage the combination of user-item rating data and item hybrid features to propose a novel <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M4"><mml:mrow><mml:mtext>CB</mml:mtext></mml:mrow></mml:math> recommendation model, which is suitable for rating-based recommender scenarios. The experimental results show that the proposed model has better recommendation performance in sparse data scenarios than conventional approaches. Besides, training offline and recommendation online make the model has higher efficiency on large datasets.