E-Commerce Personalized Recommendation Based on Convolutional Neural Network

Abstract

There is a local sparsity of user interest data in current e-commerce, resulting in low accuracy of personalized product recommendation. An item personalized recommendation model based on improved local similarity prediction of CNN (LSPCNN) is constructed. Firstly, the convolutional neural network CNN is used to extract local features. Then, a regulating layer is added on the basis of CNN network, and the item scoring matrix is constructed for the initial users to make their interest locally characterized. Finally, CNN is used to predict the missing score, thus realizing personalized recommendation. Experimental results show that compared with the improved CNN network model and the collaborative filtering recommendation model based on hybrid neural network, the data sparsity of the proposed LSPCNN model is significantly reduced, and the mean absolute error (MAE) is smaller. Therefore, the proposed algorithm can accurately extract the local feature data that users are interested in, which improves the accuracy of e-commerce personalized recommendation, and has certain feasibility.