人工智能在电商个性化推荐中的应用、挑战及治理路径
Application, Challenges and Governance Paths of Artificial Intelligence in Personalized Recommendations in E-Commerce
摘要: 在数字化时代,人工智能驱动的个性化推荐系统已成为电子商务生态的核心引擎,通过精准匹配供需关系显著提升商业效率。本文系统探讨人工智能在推荐系统中的技术应用、挑战及治理路径。研究显示,人工智能等计算机技术通过用户画像的动态构建与行为预测,实现了对用户的精准推送,以此大幅增强了用户的参与度与购买意愿。然而,技术跃进伴随深刻的伦理风险。数据隐私边界的消解、算法偏见对公平性的侵蚀等问题,均暴露了技术理性对人性尊严与社会公平的威胁。对此,本文提出“技术创新–制度约束–公众参与”协同治理框架。强调以“人的主体性”为核心重构智能商业生态,在技术创新中注入伦理自觉,最终实现从“流量攫取”向“价值共创”的范式转型。
Abstract: In the digital age, AI-powered personalized recommendation systems have become the core engine of the e-commerce ecosystem, significantly enhancing business efficiency by precisely matching supply and demand. This paper systematically explores the technical applications, challenges, and governance pathways of artificial intelligence in recommendation systems. Research indicates that computer technologies, such as AI, achieve precise user targeting through the dynamic construction of user profiles and behavioral prediction, thereby substantially enhancing user engagement and purchase intention. However, technological leaps forward are accompanied by profound ethical risks. Issues such as the erosion of data privacy boundaries and the undermining of fairness by algorithmic biases expose threats posed by technological rationality to human dignity and social equity. In response, this paper proposes a collaborative governance framework integrating “technological innovation-institutional constraints-public participation.” It emphasizes reconstructing the intelligent business ecosystem around the core principle of “human agency,” infusing technological innovation with ethical awareness, and ultimately realizing a paradigm shift from “traffic extraction” to “value co-creation.”
文章引用:陈英豪, 周蕾蕾. 人工智能在电商个性化推荐中的应用、挑战及治理路径[J]. 电子商务评论, 2025, 14(7): 878-883. https://doi.org/10.12677/ecl.2025.1472248

参考文献

[1] Nguyen, T.T., Dang, M.T., Luong, A.V., et al. (2019) Multi-Label Classification via Incremental Clustering on an Evolving Data Stream. Pattern Recognition, 95, 96-113. [Google Scholar] [CrossRef
[2] He, X., Liao, L., Zhang, H., Nie, L., Hu, X. and Chua, T.S. (2017) Neural Collaborative Filtering. Proceedings of the 26th International Conference on World Wide Web, Perth, 3-7 April 2017, 173-182. [Google Scholar] [CrossRef
[3] 赖小馨. 基于人工智能的个性化推荐系统在电子商务中的应用[J]. 知识经济, 2024(6): 37-39.
[4] Panigrahi, D. and Karuna, M. (2021) A Review on Leveraging Artificial Intelligence to Enhance Business Engagement in Ecommerce. International Journal of Research Publication and Reviews, 2, 239-250.
[5] 高广尚. 可解释推荐模型中的可解释性方法研究综述[J]. 数据分析与知识发现, 2024, 8(8): 6-19.
[6] 承上. 人工智能时代个性化定价行为的反垄断规制——从大数据杀熟展开[J]. 中国流通经济, 2020, 34(5): 121-128.
[7] 项亮. 推荐系统实践[M]. 北京: 人民邮电出版社, 2012.
[8] 汤志鹏. 短视频中的内容检测与个性化推荐算法研究[J]. 信息与电脑(理论版), 2021, 33(13): 39-42.
[9] 冯勇, 邹宝旭, 徐红艳. 视频内容特征与弹幕文本相结合的短视频推荐模型[J]. 辽宁大学学报(自然科学版), 2021, 48(2): 108-115.
[10] Wang, Y., Xu, J., Wu, A., Li, M., He, Y., Hu, J., et al. (2018) Telepath: Understanding Users from a Human Vision Perspective in Large-Scale Recommender Systems. Proceedings of the AAAI Conference on Artificial Intelligence, 32, 467-474. [Google Scholar] [CrossRef
[11] 成保梅. 基于协同过滤的电子商务个性化推荐算法研究[J]. 现代电子技术, 2019, 42(20): 37-39+44.
[12] 兰玮霞. 某大型3C电商平台在电子商务环境下的供应链管理创新实践探索[J]. 消费电子, 2025(2): 146-148.
[13] 王国霞, 王丽君, 刘贺平. 个性化推荐系统隐私保护策略研究进展[J]. 计算机应用研究, 2012, 29(6): 2001-2008.
[14] 郭楚怡. 个性化推荐系统对个人信息的“三次使用”: 大数据时代的隐私保护难题[J]. 科技传播, 2021, 13(18): 159-161.
[15] 黄英辉, 刘辉, 王伟军, 等. 心理图式在应对推荐系统用户过度特化问题中的作用: 基于机器学习的实证研究[J]. 图书与情报, 2024(4): 118-130.
[16] 尼尔·埃亚尔, 瑞安·胡佛. 上瘾: 让用户养成使用习惯的四大产品逻辑[M]. 北京: 中信出版社, 2017.
[17] Fassiaux, S. (2023) Preserving Consumer Autonomy through European Union Regulation of Artificial Intelligence: A Long-Term Approach. European Journal of Risk Regulation, 14, 710-730. [Google Scholar] [CrossRef