<![CDATA[In a high-volume market like Spotify, it's important to understand what makes an artist valuable. One way to measure the success of a song or album is to check the rankings and charts. Spotify, for example, publishes several charts. Notably, Today's Top Hits, the first number one playlist in the Spotify ecosystem, has 18.2 million followers (about 7.5 million more than the second place playlist, Spotify Global Top 50), and has about 2.5 million daily active listeners. The use of the K-Means Algorithm because this method can handle large music data effectively. The results of the clustering are expected to be used for Record Labels in showing the proportion of Artist popularity that is included in the Today's Top Hits Playlist which is expected to find out what percentage of an Artist who has a certain followers and popularity to enter the Playlist, or maybe to find out the Artist segmentation on the Playlist. As a result, in the clustering process using the K-Means method, it was found that the proportion of artists on Today's Top Hits Playlist was 28.79% for Very Popular, 42.42% for Popular, 28.79% for Unpopular. Meanwhile, in the cluster testing process using the Silhouette Coefficient, the value is 0.536, which means that the results of the cluster are well formed. Meanwhile, using the Davies-Bouldin Index shows the value is 0.554, which means that the results of the cluster are well formed too.]]>
Copyrights © 2021
