A team of researchers says they have developed an equation that helps predict which songs will become hit singles. Here is how the equation works:
We represent each song using a set of 23 different features that characterize the audio. Some are very simple features — such as how fast it is, how long the song is — and some are more complex features, such as how energetic the song is, how loud it is, how danceable and how stable the beat is throughout the song. We also took into account the highest rank that songs ever achieved on the chart.
The computer can combine a song’s features in an equation that can be used to score any given song.
We can then evaluate how accurately the computer scored it by seeing how well the song actually did.
Every single week now we’re updating our equation based on how recent releases have done on the chart. So the equation will continue to evolve, because music tastes will evolve as well.
As the researchers note, this equation is based mainly on the musical content and doesn’t factor in the content of the lyrics or budgeting for the song and music group. The equation seems mainly to be based on whatever musical styles and changes are already popular so I wonder how they account for changes in musical periods.
If this equation works well (and the interview doesn’t really say how accurate this formula is for new songs), this could be a big boon for the culture industries. The movie, music, and book industry all struggle with this: it is very difficult to predict which works will become popular. There are ways in which companies try to hedge their bets either by working with established stars/performers/authors, working with established stories and characters (more sequels, anyone?), and trying to read the cultural zeitgeist (more vampires!). But, in the end, the industries can survive because enough of the works become blockbusters and help subsidize the rest.
At the same time, haven’t people claimed they have cracked this code before? For example, you can quickly find people (like this and this) who claim they have it figured out. And yet, revenues and ticket sales were down in 2011. There is a disconnect here…