Abstract
Content-based (CB) and collaborative filtering (CF) recommendation algorithms are widely used in modern e-commerce recommender systems (RSs) 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 CB 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.
Highlights
With the vigorous development of the Internet, a large volume of data is generated everyday
It can be noticed that the proposed model has better rating prediction accuracy because hybrid feature-based KNN (HFB-KNN)’s mean absolute error (MAE) and root mean-squared error (RMSE) values are always smallest in all the scenarios of different user neighbor numbers
When the data are quite sparse, it should be noticed that the performance of HFB-KNN and content featurebased KNN (CFB-KNN) is dramatically better than that of userbased K-nearest neighbors (UserKNN). is is because both HFB-KNN and CFBKNN are based on the proposed model, which can enrich the feature matrix and get more latent information of user preferences in the sparse data scenarios. e reason why HFB-KNN outperforms CFB-KNN is that CFB-KNN only exploits content features; HFB-KNN leverages editorial features, user-generated features, and image visual features
Summary
With the vigorous development of the Internet, a large volume of data is generated everyday. Eir previous works inspired us to use image visual features of items to explore users’ potential preferences for recommendation. Content features and some other features of items can reflect users’ potential preferences to certain extent Due to these reasons, in the proposed approach, we combine user ratings and hybrid features which include all kinds of item features discussed above. By transforming user-item ratings to the ratings of hybrid features, the users’ potential preferences of hybrid features are used to find the nearest neighbors In this way, the data sparsity problem and the low efficiency problem are solved. By transforming user-item ratings to the ratings of features, we calculate users’ potential preferences of hybrid features, which include item content features, image visual features, and so on.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
