Personalized Music Recommendation model based on Machine Learning

A music recommendation system suggests songs to an individual user on his preferences. There are many different sorts of music to choose from. The world of music is so vast that it is impossible to listen to all the songs one desires. As a result, we create a model that supports a user in discovering music that he could enjoy. It collects individuals who share the user's passions and picks knowledge and resemblance associations depending on the user's past. The information gathered from user evaluations is used to make suggestions. The main focus of the study is on the context-aware recommendation process's insufficient integration of context data with the emergence of new attractions. Using libraries like NumPy and Pandas, we used a library of songs to uncover connections across individuals and music so that a hit album might be offered to individuals derived from history. In addition to Count Vectorizer (CV), we'll use Cosine similarity (CS). In addition, when a piece of given music is processed, a front end with a flask will provide us with the suggested tracks.