Music Recommendation System using Machine Lea...

Music Recommendation System using Machine Learning

Author Name : K Madhu Chandra Prasad, Dr Nachappa MN

ABSTRACT

The music recommender can anticipate and afterward offer fitting songs to their clients utilizing a music recommender framework in view of the attributes of past music heard. We assembled, developed, and surveyed a music proposal framework for this task. We used Kaggle's Million Song Dataset to reveal associations among clients and tunes, as well as to gain from clients' earlier listening conduct to create ideas for tunes they would need to pay attention to the most. We will detail the approaches we utilized, as well as the results and their investigation, in this paper. For the collaborative sifting calculation, we accomplished the best outcomes. We've likewise made a popularity-based model that pursues the direction. Music proposal can be a troublesome issue since we need to structure music so that we can prescribe songs to clients who don't have a particular inclination. It's liquid, and it's occasionally affected by factors other than a client's or alternately music's listening history.

Key Words: recommendation systems, music, Million Song Dataset, collaborative filtering, content-based, popularity-based, Machine Learning (ML).