If I had a nickel for every time I’ve heard someone claim “Oh those radio hits all sound the same,” I could fund a trip to Coachella for my friends and I to prove that statement’s actual relevance. In all seriousness though, pop songs have become so formulaic, that a computer algorithm can now predict the likelihood of a track’s commercial success. Don’t believe me? Check the numbers from this year’s top “dance singles” from Billboard, as the algorithm successfully predicted at least a 60% probability of ‘hit’ status for the entirety of the top 10:
Billboard 2015 Hot Dance/Electronic Songs (via billboard.com)
“Lean On” by Major Lazer & DJ Snake Featuring MØ — 82%
“Where Are U Now” by Skrillex & Diplo With Justin Bieber — 72%
“Hey Mama” by David Guetta Featuring Nicki Minaj, Bebe Rexha & Afrojack — 72%
“You Know You Like It” by DJ Snake & AlunaGeorge — 63%
“Waves” by Mr. Probz — 68%
“Outside” by Calvin Harris Featuring Ellie Goulding — 82%
“Prayer In C” by Lillywood & Robin Schulz — 65%
“Blame” by Calvin Harris Featuring John Newman — 88%
“How Deep Is Your Love” by Calvin Harris & Disciples — 62%
“I Want You To Know” by Zedd Featuring Selena Gomez — 89%
The algorithm was formulated by an analysis team at the ANT/OR research group at Antwerp University in Belgium. To efficiently predict the probability of a song’s commercial success, it analyzes 139 different elements of its inherent structure and ‘timbre’ – or how it might make you feel. This vast investigation includes obvious aspects such as length and tempo, but also more subjective features like danceability and brightness/gloominess. According to one of the study authors, Dorien Herremans, popular songs share a certain set of features that make them appealing to the general public, and you can test any new song against those very aspects to predict its commercial potential. Although the algorithm leaves out certain factors such as the current social taste and artist name recognition, I think it’s safe to say those things can be massive influences as well.
H/T: VICE
