A Literature Review of Machine Learning Techniques for Recommender System In E-Commerce

Abstract

The swift expansion of e-commerce has prompted the creation of advanced recommender systems to augment user experience and boost sales. Machine learning techniques have become fundamental for the development of these systems, allowing firms to provide tailored product recommendations based on customer preferences and habits. This research presents a thorough literature assessment of machine learning methodologies utilized in recommender systems, emphasizing their predictive efficacy in the e-commerce sector. We analyze essential methodologies, including collaborative filtering, content-based filtering, hybrid models, and sophisticated techniques such as deep learning. Through the examination of 38 research in the domain, we elucidate the limitations, advantages, and possibilities of machine learning algorithms in delivering precise and scalable suggestions. Our research indicates that hybrid models, which integrate many recommendation strategies, demonstrate significant potential in addressing challenges like the cold start problem and data sparsity. The report delineates prospective research avenues, underscoring the necessity for continued innovation in the integration of machine learning into recommender systems to improve accuracy and customer happiness in e-commerce settings.