COMPARATIVE ANALYSIS OF RECOMMENDATION ALGORITHMS FOR DETERMINING PERSONAL PREFERENCES BASED ON NEURAL NETWORKS

Yang T., Afanasyev G. I., Kalistratov A. P., Afanasyev A. G.

In this paper, we study several popular recommendation algorithms. Among the many personalized recommendation algorithms, the collaborative filtering algorithm has become one of the most widely used technologies due to its simplicity, efficiency, and accuracy. Based on existing research, this article combines Slope One's advanced weighted method with deep learning autoencoder to learn deeper features of the dataset while alleviating the problem of data sparseness, thereby improving the quality of recommendations.

Keywords:personalized recommendation, scoring matrix, deep learning autoencoder, neural networks