How To Predict A Song Will Be A Hit

How can we predict that a song is gonna be a hit or a flop? What if science could predict it? A research team, led by Dr. Tijl de Bie and based in the University of Bristol’s Intelligent Systems Laboratory in the Faculty of Engineering, has done some research about this specific problem and a paper was presented last Saturday at the 4th International Workshop on Machine learning and Music.

To study this, they looked at the UK top 40 singles chart over the past 50 years, in particular studying the 5 most popular songs and the least popular ones, according to certain musical features, i.e. tempo, time signature, song duration, loudness, harmonic and chord sequence simplicity, and also how noisy the song was…. They actually looked at 23 features.

Then, researchers came up with an equation, the ‘hit potential equation’, that is supposed to give a score to the song according to all these features, and so classify a song into a hit or non-hit position based on this score.

Since they were studying songs of the past, they could actually check their predictions, and their system had an accuracy rate of 60%, which may not seem very good, but when dealing with complex and unpredictable things such as pop-culture tastes, it is an impressive result.

The biggest problem was to take into consideration the time period, as a hit of the 60s is obviously very different from a hit of the 90s, and this is why Dr. Tijl de Bie explained they adapted the equation according to the period:

‘Musical tastes evolve, which means our ‘hit potential equation’ needs to evolve as well. Indeed, we have found the hit potential of a song depends on the era. This may be due to the varying dominant music style, culture and environment.’

So how can we really predict a hit? May be we can’t totally, but I think that the best part of the study was precisely how this hit potential has evolved over the years:

‘- Before the eighties, the danceability of a song was not very relevant to its hit potential. From then on, danceable songs were more likely to become a hit. Also the average danceability of all songs on the charts suddenly increased in the late seventies.

– In the eighties slower musical styles (tempo 70-89 beats per minute), such as ballads, were more likely to become a hit.

– The prediction accuracy of the researchers’ hit potential equation varies over time. It was particularly difficult to predict hits around 1980. The equation performed best in the first half of the nineties and from the year 2000. This suggests that the late seventies and early eighties were particularly creative and innovative periods of pop music.

– Up until the early nineties, hits were typically harmonically simpler than other songs of the era. On the other hand, from the nineties onward hits more commonly have simpler, binary, rhythms such as 4/4 time.

– On average all songs on the chart are becoming louder. Additionally, the hits are relatively louder than the songs that dangle at the bottom of the charts, reflected by a strong weight for the loudness feature.’

If I summarize, power ballads were big in the 80s, the late 70s-early 80s were the most creative, people had simpler tastes before the 90s (or were dumber), and we are all gonna be deaf soon.