2y ago

Machine Learning Unlocks the Secret to Hit Songs

nexlumina.com Machine Learning Unlocks the Secret to Hit Songs

Researchers harness neurophysiology and machine learning for 97% accuracy in predicting future chart-toppers.

Why it matters: A recent study at Claremont Graduate University has applied machine learning to neurophysiological data, identifying hit songs with an astonishing 97% accuracy.

Read the Research article.

Discussion on Hacker News.

You're viewing a single thread.

9 comments

I'm increasingly convinced that the pop music of the future will consist entirely of mediocre or terrible songs written by real people -- that the flaws and fuck-ups of lousy artists will suddenly seem like magic when compared to an endless stream of algorithmically generated, pristine computer bullshit.
- It seems likely to me that 'pop' music won't be created by people. As a result, people won't be made famous through music anymore, the cult of celebrity will move on to be more era-appropriate.
  I mean, this only happened in the first place because it was extremely profitable to sell lots of records/concert tickets. That doesn't seem to be the case now.
  So, if pop music has been manufactured to sell an image to impressionable people, there's little incentive to do that these days. It's surely more lucrative to fund an influencer than a 'musician'.

9 comments