Log In

Enter your username and password below

Algorithm Charts the Way to Music Success

Adele is one of the stars set to perform at Sunday’s Grammy Awards. Her song, “Rolling in the Deep,” was an international smash hit last year.

Critics say Adele’s unique voice, allied with extensive marketing, could have been the reasons for its success.

But not according to Bristol-based scientist, Dr. Tijl De Bie.

He believes the track’s triumph was the result of meeting a strict 23-character criteria of an algorithm devised by his students:

“The features that contributed to a good score for Adele were its energy, so it wasn’t too energetic, for the time when it was released. There was some variability in the beats and it was somewhat danceable, although not very danceable.”

The team believes that pop music is a science. And they’ve programmed every song from the U.K.’s Top 40 singles chart since 1960 into a computer to prove it.

De Bie explains:

“The score of the song is computed as a linear combination of several feature values that are automatically extracted from the audio of the music. These feature values relate to the various aspects – like the duration of the song, how fast it is, which is quantified by the number of beats per minute, or the time signature automatically from the audio itself. There are more complex things such as the danceability of the song, how much energy there is in the song and the harmonic complexity.”

De Bie says the “Score a Hit” formula has a 60% accuracy rate.

“Just the Way You Are” by Bruno Mars topped the charts in nine countries last year. But what did the formula make of its potential? De Bie says:

“The score that we got from it was quite an average score, as well, although slightly to the hit side. So that means that we would have categorized it as a hit, but only very marginally so.”

One of the biggest hits of the 1980s was Kylie Minogue’s “I Should Be So Lucky.” Its co-writer, Mike Stock, has written or produced more than 100 Top 40 records.

What does he make of the scientists’ algorithm?

“If you’re just doing something that the computer tells you to do because it’s been a hit before, you’re not interested in that. You want to know what the next hit’s going to be. Why would you want to think that a software device has come up with something you’re supposed to feel and believe in? It’s music, it’s supposed to touch you.”

The United Kingdom’s prestigious Christmas number one slot was an unlikely choice – a charity record by the Military Wives Choir.

De Bie admits this song turned his team’s equation upside down:

“That didn’t do well on danceability at all. It didn’t do well on loudness, it had a very clean harmonic sound, and harmonically, musically speaking, it was a relatively easy song, whereas most of the time the hits are slightly more complex than the non-hits. So you could say it’s a surprise that it still became a hit, but of course there is the social aspect surrounding it that in this case made all the difference.”

De Bie’s team is working with companies to commercialize the software, while an iPhone app is also in development.

Whether songwriters will use “Score a Hit” to gauge their song’s hit potential remains to be seen, but it’s fair to say that this year’s Grammy judges probably won’t be relying on algorithms to announce the big winners of 2011.