Unifying user preference and item knowledge-based similarity models for top-N recommendation

Recommendation systems are very important in various applications and e-commerce environments. A representative method is collaborative filtering (CF), which models the user preference by means of feedback from the user. CF-based methods made better recommendations than did previous studies because CF captures the interactions between the user and the item. However, despite the advantages of working with high-density data, these methods are vulnerable to the data sparsity that often exists in real data sets. In addressing this issue, we combine similarity-based approaches (which clearly serve product recommendations that are similar products) with knowledge-based similarity and provide individualized top-N recommendations. This approach, called UK (Unifying user preference and item knowledge-based similarity models), further exploits knowledge-based similarity ideas along with user preferences to extend the item interactions. We assume strong independence between various factors. We quantitatively demonstrate that by applying our method to real data sets of various sizes or types, UK works better than cutting-edge methods. In terms of qualitative discovery, UK also understands individual interactions and can provide meaningful recommendations according to the goal.