The rise of digital music platforms has made customized music recommendation systems more important than ever. This study suggests an automated musical recommendation system that uses listener preferences to improve user satisfaction. The system utilizes machine learning techniques to examine user behavior, including hearing the past, genre preferences, emotions, and environmental variables. The system creates personalized music suggestions by using collaborative filtering methods, content-based filtering, as well as hybrid approaches to match the specific interests and preferences of each listener. The system also includes feedback systems to constantly improve suggestions and adjust to changing customer tastes over time. The evaluation findings confirm that the suggested approach is successful in delivering precise and relevant music suggestions, thus improving user pleasure and involvement. The technology shows potential for enhancing music exploration and cultivating a more customized and pleasurable listening experience for consumers on different digital music platforms