The science behind a hit song, and why it's hogwash

I have to digress from posting about real music to share this recent article from The Los Angeles Times: "The science behind what makes a hit single." It starts hopefully enough. After lamenting that predicting what becomes a hit is "more a matter of alchemy than science," the piece asserts "[n]ow European researchers are challenging that notion. Using 50 years' worth of hit songs on Britain's top 40 charts, they've come up with a computer program that can predict whether a song will catch fire on the airwaves or fizzle out."

The researchers are so confident that they've even built an app.

Using an artificial intelligence program, project leader Tijl De Bie and his team came up with an equation that they claim has predictive powers. Using a database of previous hit songs, and identifying twenty-three different musical "features" such as length, loudness, energy and beat stability, the program can identify a song with hit potential. De Bie points out three successful guesses - Wiley's "Wearing My Rolex," Gnarls Barkley's "Crazy," and Elvis Presley's "Suspicious Minds."

I'm really not sure about the last one. "Suspicious Minds" was a big hit over 40 years ago, so we can say with total authority that the program can identify past hits with startling accuracy. Especially if that information has already been fed into the computer.

De Bie goes on to identify musical trends that have developed over the past fifty years, but stops short about what's to come. "If you're asking if music is going in a single direction," he advises the interviewer, "I don't think that is the case. I think it will continue to evolve in fairly unpredictable ways. Our equation is trying to be resilient to that by learning mostly from the most recent songs..."

This begs the question about the purpose of this exercise at all, but it gets better. The project leader ends the piece by predicting for his own work's irrelevancy:

"...If everyone starts using this method - starts making music lacking any creativity that just tries to satisfy this equation - then I think people will soon start longing for something new, which means the equation will somehow defeat itself."

Upon hearing this latest drumbeat for the March of Folly, two things come to mind. One is that there will be some musicians who use this app to somehow divine public taste, and maybe one of them will succeed. As the great H.L. Mencken said, "Nobody ever went broke underestimating the intelligence of the American public."

The other thing that came to mind is this computer program's fellow traveler, The Useless Machine: