Optimizing E-commerce Recommender Systems: A Comprehensive Review of Techniques and Future Directions
Z. Helen Wu · Applied and Computational Engineering · 2024
This paper examines recommender systems in e-commerce by reviewing technologies and real-world applications and identifying the importance of big data analytics in recommender systems. In the study, three kinds of recommendation algorithms are discussed: collaborative filtering, content-based recommendation, and hybrid models. Collaborative filtering methods did well in the case of large-scale user data, but had cold-start and sparsity problems. Based on the content, recommended methods have strong personalized suggestion functions, but the “information cocoon” phenomenon is a risk, which decreases the contents’ diversity. Hybrid models are a combination approach between the two techniques, providing a flexible and robustness solution, but only a more complex computationally. This article also looks at the technology trends that have emerged lately, for example, the use of deep learning models, as well as the privacy-preserving techniques utilized in recommender systems. By analyzing and summarizing the existing research, this paper provides a reference basis for future optimization and application of recommender systems and points out potential research directions.