I will be using the features provided by the Spotify API: danceability, acousticness, key, speechiness, liveness, energy, valence and instrumentalness. All these are well explained here.
In addition to that, I have created a new interesting metric called versatility, a combination of the prior with unsupervised learning. Basically, all the features in an array form a point in an eight-dimensional space (a matrix of 8 items). If we use all the tracks of an artist, playlist or whatever, we obtain a map of points that can be clustered and represented in 2 or 3 dimensions (in this case I have used HDBSCAN and UMAP). If the result is a small number of clusters, this indicates that the singer does not have a variety of registers, he would be monotone. Whereas in the other case he/she would be considered to be versatile, varying their tracks frequently. Let´s see an example:
These are Kanye West and Tyga charts of versatility. As you can see, Kanye shows a great variety of styles (10 clusters). On the other hand, Tyga is less versatile, with only 2 clusters.
- Who is the most versatile artist?
This is a very difficult question. Unfortunately, we cannot scrap Spotify Charts anymore, so I have searched through this page to get the list of the 300 most viral artists since 2013. This can be easily done with these lines:
Surprised? DJ Tiestö and Diplo seem to be the most versatile artists with 12 clusters. Nevertheless, I have notice that there is a tendency among DJs and reggaeton singers to be on top and this may be because they are the artists with most feats (tracks with other artists). This is the top 10 most versatile artists. I recommend you to check it yourself listening to them!