ARCHIVES

Abstract: The Music Recommendation Systems have evolved significantly, leveraging user data to provide personalized listening experiences. While previous studies, such as those utilizing random forest regressors for recommending sad music, have shown promising results, there is a growing need to develop more versatile systems that can recommend a diverse range of music genres. This system addresses the need by employing the K-Nearest Neighbors (KNN) algorithm to recommend a variety of music based on users’ historical interactions and preferences. The primary goal of this research is to build a comprehensive music recommendation system that suggests a broad spectrum of music genres. This system uses KNN to analyze user listening histories and identify preferences based on the tastes of similar users. The project aims to enhance the personalization of music recommendations beyond the scope of specific genres or emotions. The KNN based recommendations system effectively provides diverse music recommendations by analyzing user history and similar user tastes. The model generates a list of recommended songs that span multiple genres, tailored to the individual user’s preferences. This system demonstrates the applicability of the KNN algorithm in developing a versatile music recommendation system that accommodates a wide range of music genres. The system’s ability to provide personalized recommendations based on user history and similarity to other users enhances the overall listening experience. Future improvements could include integrating additional features and advanced algorithms to further refine recommendations and cater to evolving user preferences.