Music Playlist Recommender System AFT-IS

Abstract

Previously, we had proposed a playlist recommendation method to suggest music by considering the change in acoustic features in the song so that the transition between songs becomes smooth. Our previous method uses the last two songs in a playlist to make recommendations for following songs that have a smooth transition of acoustic features from the current songs. However, in this previous method, if two or more songs are not given, it is not possible to recommend a suitable next song. Our method proposed in this paper considers the transition of the music that was last played and recommends the next song. Moreover, we have developed a playlist recommender system using our proposed method. As the user inputs information necessary for creating a playlist, the system outputs a playlist with a smooth transition of acoustic features.