Recommendation prediction method based on attribute information reference self-leaning

Abstract

The invention relates to a recommendation prediction method based on attribute information reference self-leaning. Attribution information is utilized for slowing down cold start, the advantages of user and commodity collaborative filtering and model decomposition based on a matrix are combined, the training speed is high, and the interpretability is achieved; meanwhile, on the condition that rating data is sparse, the prediction precision is superior to that of user and commodity collaborative filtering and the matrix-based decomposition method.

Description

technical field [0001] The invention relates to a recommendation prediction method, in particular to a recommendation prediction method based on attribute information preference self-learning. Background technique [0002] The recommendation system is a popular research direction at present, and its purpose is to mine relevant information from massive user data to recommend products to users. For users, the recommendation system can recommend products that better meet the needs of users. On the other hand, for sellers, the recommendation system can use existing information to recommend products to expand sales. However, there are sparsity and cold start problems in recommender systems, which limit the application of recommender systems to a certain extent. [0003] Recommendation methods can be mainly divided into two types, content-based recommendation methods and collaborative filtering methods. The content-based recommendation method needs to manually label information...

AI Technical Summary

Problems solved by technology

[0005] However, the classic user and product collaborative filtering method has the problem of long training time, and the long training time based on matrix decomposition is insufficient in interpretability.

Images