Music Recommendation System using Case-Based Reasoning Method

The choice of music in the playlist may differ according to the activities carried out at a certain time. A music recommendation system that can simultaneously create playlists for users based on certain activity and/or mood can reduce the time it takes for music listeners to find suitable music and make music playlists to listen to. In this research, the music recommendation system will use listening history data from music listeners and the Case-Based Reasoning method. Music listening history data consists of listener context data (gender and age), music data (artist and title), and other context data (time, desired mood, current weather, and activity). Context data is used because the latest developments in recommendation systems and music information retrieval have shown that context data is important data that can produce personalized recommendation results. The Case-Based Reasoning method generates recommendations by selecting the listening history data that is in accordance with the current state of the listener. System evaluation was carried out and obtained a 0.66 precision value based on user preferences, which indicates that 66 % of the recommendations provided by the system are suitable for the user.