Machine-learning engineers from the University of Bristol think they might have the master equation to predicting the popularity of a song.

The so-called Hit Potential Equation looks a little something like this:

Score = (w¹ x f¹) + (w² x f²) + (w³ x f³) + (w⁴ x f⁴), etc.

Simple, right? The “w”s are “weights,” or musical features like tempo, time signature, song duration, loudness and how energetic it is. By using a machine-learning algorithm, the team could mine official U.K. top-40 singles charts over the past 50 years to see how important these 23 features are to producing a hit song. via Wired

Continue reading