In our research, we build a music recommendation system to make prediction of users' listening preference.

A recommendation system is a type of filtering system that predicts a user's preferences for a specific item. Its purpose is to suggest items that the user might find appealing. In our research, we build a music recommendation system to make prediction of users' listening preference. Our system extends the previous T-RECSYS algorithm which uses a hybrid of content-based and collaborative filtering as input to a deep learning classification model. We enhance the performance of this algorithm by incorporating the latest Spotify API, which provides access to 11 music features including danceability, liveness, tempo and so forth. Additionally, we leverage more advanced deep learning models to achieve a higher level of precision and accuracy in our recommendations. In detail, we promote the precision scores from the original 88% to the current over 95%.

Explore More!

Research Paper

Source Code