电子商务推荐系统公平性研究进展  

Research Progress on Fairness of E-commerce Recommendation System

作　　者：喻继军 熊明华 YU Jijun;XIONG Minghua(School of Information Engineering,Shanwei Institute of Technology,Shanwei 516600;Business School,Foshan University,Foshan 528225,China)

机构地区：[1]汕尾职业技术学院工程学院,广东汕尾516600 [2]佛山科学技术学院经济管理学院,广东佛山528225

出　　处：《现代信息科技》2023年第14期115-124,共10页Modern Information Technology

基　　金：广东省教育厅普通高校特色创新类项目(2021WTSCX243)。

摘　　要：随着电子商务的快速发展,推荐系统作为大数据环境下解决“信息过载”问题的有效工具已广为使用。受数据、算法、人为干预等因素的影响,推荐系统可能会为具有某些属性的消费群体提供不公平的推荐结果从而导致各种问题。近年来,研究者们提出各种解决推荐系统公平性问题的方法。文章总结了近几年的研究成果,从两个方面总结归纳了造成电子商务推荐系统公平性问题的主要原因,并给出五种主要的解决方案;介绍了当前可供研究的数据集及工具,也对电子商务推荐系统公平性研究尚存的问题及未来的研究方向进行了探讨,以期为该领域的研究人员提供参考。With the rapid development of E-commerce,recommendation systems have been widely used as an effective tool to solve the problem of“information overload”in the big data environment.Due to factors such as data,algorithms,and human intervention,recommendation systems may provide unfair recommendation results for consumer groups with certain attributes,leading to various problems.In recent years,researchers have proposed various methods to address the fairness issue of recommendation systems.This paper summarizes the research achievements in recent years,summarizes the main reasons for the fairness issues in E-commerce recommendation systems from two aspects,and provides five main solutions.It introduces the current available datasets and tools for research,and explores the remaining issues and future research directions in the fairness of E-commerce recommendation systems,with the aim of providing reference for researchers in this field.

关 键 词：电子商务 推荐系统 算法公平性 数据偏差 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] F274[自动化与计算机技术—计算机科学与技术]