A former band mate of mine once told me he would be happy to have a one-hit wonder. I thought he was crazy. I wanted a long life full of hits (and fame and groupies and all that comes with the rock-n-roll lifestyle). One-hit wonders seemed so fleeting and defining.

Besides, a musician doesn’t set out to write one hit song and then retire for life. If that happened, hit songs would be easy to craft and more people would do it.

But stop the record. A new study has found what it takes for a song to be a hit. University of Bristol researchers claim that predictions can be made using machine learning algorithms.

The team looked at the official U.K. top 40 singles chart over the past 50 years. Their aim was to distinguish the most popular (peak position top five) songs from less popular singles (peak position 30 to 40).

The researchers used musical features such as, tempo, time signature, song duration and loudness. They also computed more detailed summaries of the songs such as harmonic simplicity, how simple the chord sequence is, and non-harmonicity, how ‘noisy’ the song is.

A ‘hit potential equation’ that scores a song according to its audio features was devised. The equation works by looking at all the U.K. hits for a certain time and measuring their audio features. From this the researchers had a list of weights, telling then how important each of the 23 features was and allowing them to compute a score for a song.

The researchers classified songs as hits or not-hits based on their scores. The team had a 60 percent accuracy rate and noticed some interesting trends.

• Before the 1980s, 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 1970s.
• In the 1980s, 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 1990s and from the year 2000. This suggests that the late 1970s and early 1980s were particularly creative and innovative periods of pop music.
• Up until the early 1990s , hits were typically harmonically simpler than other songs of the era. On the other hand, from the 1990s 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.

You can read more about the research at ScoreaAHit.

My favorite trend is the part about the late 1970s and early 1980s as periods of more creative and innovative music. I definitely agree with that.

Now, if you’ll pardon me, I have a hit song to write. The secret formula has been found.

(Photo via Flickr: Paul Townsend / Creative Commons)

Send to Kindle