Machines will help pick out the next big pop song

John Moe Jun 22, 2011

Scientists at Emory University have found out how to predict a product’s popularity – and when I say product, I mean teeny-bop music. The researchers took MRI scans of teenagers who listened to songs on myspace. Then they let the data sit for a few years.

From Scientific American:

During that time, the songs did what songs will do. A tiny percentage became extremely popular, a handful more became somewhat popular, and the overwhelming majority went nowhere. After tallying the sales information for each song, the scientists essentially took a shot in the dark. They re-examined brain areas associated with song likability years ago, and asked if activity in those areas predicted a song’s eventual success.
For one area — the nucleus accumbens – the answer was yes. Though it certainly didn’t distinguish between hits and duds with dead-on accuracy, more activity in the accumbens was loosely predictive of higher sales.

Even though there’s a lot more work to be done here to get any solid conclusions, it’s a big step for neuromarketing.

As a nonprofit news organization, our future depends on listeners like you who believe in the power of public service journalism.

Your investment in Marketplace helps us remain paywall-free and ensures everyone has access to trustworthy, unbiased news and information, regardless of their ability to pay.

Donate today — in any amount — to become a Marketplace Investor. Now more than ever, your commitment makes a difference.