A Machine Can Now Predict The Next Dance Hit, And Here’s How

© Al Powers, PowersImagery.com

It’s hard to disagree that making hit songs carry a recipe these days. Hit the magic BPM number, select a sick bassline and the perfect synth work. And there you have it. Apparently songs have become so much of a formula involved affair, a computer algorithm can predict with above average accuracy the possibility that a song will top the charts. Need proof? Here are the stats from the algorithm as it successfully predicted at least a 60% probability of ‘hit’ certification for all of the Top 10 Billboard 2015 Hot Dance/Electronic Songs :

“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%

Still have a hint of doubt? Here are the dance and electro pop songs on the UK Official Charts Top 10 singles of the year that were tested and received similar results.

Official Charts Company 2015 Singles

1. “Happy” by Pharrell Williams — 83%
2. “Rather Be” by Clean Bandit — 74%
3. “All Of Me” by John Legend (not dance)
4. “Waves” by Mr Probz — 68%
5. “Thinking Out Loud” by Ed Sheeran (not dance)
6. “Ghost” by Ella Henderson — 79%
7. “Timber” by Pitbull ft. Kesha — 90%
8. “Stay With Me” by Sam Smith (not dance)
9. “Let It Go” by Idina Menzel (not dance)
10. “All About That Bass” – Meghan Trainor — 87%

The algorithm is the creation of an analysis team at the ANT/OR research group at Antwerp University in Belgium. They took a look at 139 different musical aspects to analyze songs which included basic features like length, tempo, time signature, key, and loudness alongside more technical features like beat, energy, and danceability and even more elusive qualities like a song’s timbre or tone color, or in short the overall feel of the track. And the find gave a clear indication that popular songs share a certain set of features that make them appealing to the majority of people. It is justifiable to say that the current algorithm does not look into other important factors such as the artist itself, social mood, marketing etc. but it is very much a work in progress. The research also led to an interesting discovery that dance hits have become louder and faster over the years, but their “danceability” has actually decreased.

Considering their extensive research and credibility, this surely can be taken as a concrete source and as science continues to evolve, research in this field is set to become the next big thing.

Source : VICE