Published Paper Details:

The Music Recommendation System is a machine learning-based approach that enables the music provider to anticipate customer preferences and recommend relevant songs based on the properties of previously heard music. This proposed system revolves around two major components, i.e., user data and content data. The user data consists of various factors like listening history, ambiance, time, genre, etc. After considering all the factors, a pathway is created to recommend the songs accordingly. To build the proposed system, we have to import certain libraries such as NumPy, Pandas, Matplotlib, and Seaborn, which are data processing and visualization libraries. It is required to have selection of similarity metric like cosine similarity, then the model must score each candidate according to this similarity metric and thereafter the system will recommend according to this score. In this work, mainly implementation of a Collaborative Filtering Mechanism is done thus, the system will only be able to make recommendations based on that specific user's interests. Using the K-means clustering algorithm, suggestion of music can be performed that is similar to a user's preferences even if they enjoy different genres. For our proposed model, chosen input is the respective dataset, and the output is the recommended songs.