Recommender systems play a crucial role in enhancing user experience through personalized item recommendations. This paper comprehensively reviews the evolution of recommender systems from 2017 to 2024, connecting theoretical advances with practical applications. It explores traditional techniques such as content-based filtering and collaborative filtering, as well as advanced methods including deep learning, graph-based models, reinforcement learning, and large-scale language models. It also discusses specialized systems such as context-aware, review-based, and fairness-aware recommender systems. The primary goal of this research is to bridge theory and practice, addressing challenges across diverse fields such as e-commerce, healthcare, and finance, emphasizing the need for scalable, real-time, and reliable solutions.
