Application of NGCF-Shallow Tower Algorithm in Mining AI Model Answer Recommendation System
DONG Zhongze
Abstract：In order to improve the accuracy and relevance of mining artificial intelligence models in answer recommendation systems,and reduce the error caused by time bias on the accuracy of recommended answer algorithms.A NGCF-Shallow Tower recommendation algorithm was proposed based on Neural Graph Collaborative Filtering(NGCF).The algorithm obtains recommended objects for the target user by inputting the interaction social network and temporal characteristics of the user and object.Compared with other recommendation structures,this algorithm can compensate for the influence of time characteristics of users and objects on user selection.Tests conducted on the Gowalla dataset and Hetrec2011-delicious-2k dataset showed that compared to the original NGCF algorithm,this algorithm improved accuracy by approximately 1.5％on the Gowalla dataset.In the experiment on the Hetrec2011-delicious-2k dataset,the accuracy can be improved by 4.42％.
Keywords：recommendation algorithmtime biasneural graph collaborative filtering
Publication Date：2025-06-30
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 35-39,44 )