Collaborative Filtering Recommendation Algorithm Based on Semi-Autoencoder

To effectively use the user-item interaction history and auxiliary information in recommendation systems,this paper proposes an improved collaborative filtering recommendation algorithm.Based on semi-autoencoder,the features of auxiliary information of users and items are extracted,and then mapped into the Matrix Factorization(MF) model.By using the back propagation algorithm,the semi-autoencoder and the matrix factorization model are jointly updated to improve the recommendation performance.Experimental results on the public datasets of MovieLens-100K and Book-Crossing show that the proposed algorithm provides better recommendation effects than the traditional recommendation algorithms,including the Biased Singular Value Decomposition(Biased SVD) and the Probabilistic Matrix Factorization(PMF) algorithm.

# Computer engineering. Computer hardware # Computer software # collaborative filtering|semi-autoencoder|auxiliary information|feature extraction|interaction history

ZHANG Haobo, XUE Feng, LIU Kai (2021). "Collaborative Filtering Recommendation Algorithm Based on Semi-Autoencoder". Jisuanji gongcheng. https://doi.org/10.19678/j.issn.1000-3428.0056700