Emerging synergies between large language models and machine learning in e-commerce recommendations

作者：Xiaonan Xu, Yichao Wu, Penghao Liang, Yuhang He, Han Wang · 发表于：Applied and Computational Engineering · 年份：2024 · DOI：10.54254/2755-2721/69/20241512 · 被引用次数：14 · 研究领域：Big Data and Business Intelligence

This paper explores the integration of large language models (LLMs) into collaborative filtering algorithms to enhance recommendation systems in the e-commerce domain. The proposed approach combines user-based and item-based collaborative filtering with LLMs to improve recommendation accuracy and personalization. Specifically, the study introduces a novel framework called PALR, which leverages LLMs to refine user-item interactions and enrich item representations. PALR utilizes historical user behavior data, such as clicks, purchases, and ratings, to guide candidate retrieval and generate recommended items. This study highlights the importance of integrating LLMs into recommendation systems to deliver more accurate and personalized suggestions, ultimately improving user satisfaction and driving sales in e-commerce platforms.