The application of transfer learning on E-commerce recommender systems

Nowadays, recommender systems occupy an increasingly important position in people's lives. Recommender systems are widely applied in e-commerce websites, they discover users' potential consuming habits by analyzing their behaviors, and then recommend users with what they may purchase. However, recommender systems on e-commerce sites are facing the problem of data sparsity. Data sparsity may cause poor recommendations, thereby reducing users' shopping satisfaction. In order to alleviate this problem, we propose a new approach based on the idea that combines user-based collaborative filtering techniques with transfer learning. The method alleviates the data sparsity problem by transferring the knowledge learned from dense data set to sparse ones. We use the data from a glasses site as the dense data set and the data from an underware site as the sparse one, experiments are conducted for evaluating the proposed method in this paper. Results show that our method can alleviate the data sparsity problem and improve the effect of user based collaborative filtering method.