SGT:Session-based Recommendation with GRU and Transformer

作     者：Lingmei Wu Liqiang Zhang Xing Zhang Linli Jiang Chunmei Wu 

作者机构：School of Mathematics&Computer ScienceGuangxi Science&Technology Normal UniversityLaibinGuangxi546199China 

出 版 物：《Journal of Computer Science Research》 (计算机科学研究（英文）)

年 卷 期：2023年第5卷第2期

页      面：37-51页

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the Scientific Re­search Basic Ability Enhancement Program for Young and Middle-aged Teachers of Guangxi Higher Education Institutions,“Research on Deep Learn­ing-based Recommendation Model and its Applica­tion”(Project No.2019KY0867) Guangxi Innova­tion-driven Development Special Project(Science and Technology Major Special Project) “Key Tech­nology of Human-Machine Intelligent Interactive Touch Terminal Manufacturing and Industrial Clus­ter Application”(Project No.Guike AA21077018) “Touch display integrated intelligent touch system and industrial cluster application”(Project No.:Guike AA21077018-2) National Nat­ural Science Foundation of China(Project No.:42065004) 

主　　题：Recommender system Gated recurrent unit Transformer Session-based recommendation Graph neural networks 

摘      要：Session-based recommendation aims to predict user preferences based on anonymous behavior *** research on session-based recommendation systems has mainly focused on utilizing attention mechanisms on sequential patterns,which has achieved significant ***,most existing studies only consider individual items in a session and do not extract information from continuous items,which can easily lead to the loss of information on item transition ***,this paper proposes a session-based recommendation algorithm(SGT)based on Gated Recurrent Unit(GRU)and Transformer,which captures user interests by learning continuous items in the current session and utilizes all item transitions on sessions in a more refined *** combining short-term sessions and long-term behavior,user dynamic preferences are *** experiments were conducted on three session-based recommendation datasets,and compared to the baseline methods,both the recall rate Recall@20 and the mean reciprocal rank MRR@20 of the SGT algorithm were improved,demonstrating the effectiveness of the SGT method.