Which decades are responsible for the most enduring Christmas hits? And why going up against Bublé might be ill-advised.
What does 2 years of Spotify Top 200 charts from the UK and Global tell us about the difference in music preferences?
Can you tell how popular an artist is, just by analyzing a single song? Can you tell in advance how many streams that song will get on Spotify?
In this small-scale pilot study, a collaboration between Musiio and Meddling A&R, we aim to determine whether our Hit Potential Algorithm can be used to predict the success of a song and the size of that song’s artist(s)’ fanbase.
The question of gender equity is an important one in the music industry, and data has the power to stimulate useful discussions that can lead to change. So we decided to ask: are men and women equally represented in popular music? And if representation is not equal, why?
To answer these questions, we gathered the last 2 years of Spotify Top 200 Weekly charts – 104 weeks in total. Every week, 200 songs make it to these charts by virtue of their streaming numbers. That’s 20800 songs in total. After eliminating duplicates, we found that there were only 1806 unique songs. We analyzed these songs and our results are as follows:
There are many tempos for songwriters and producers to choose from. Is there a way to know which ones are most likely to lead to a commercially successful work? We studied a total of ~6000 songs and uncovered some striking tempo choice trends.
Chartmetric’s Trigger Cities were driven by rigorous analysis of user behavior. The question is, are there any underlying, purely musical factors driving this behavior? We use our AI to investigate.
Many commercial music decisions are made based solely on gut feel. But given that 21m+ tracks are released on streaming platforms yearly, A&R executives know what it’s like to be inundated in low quality demos. The question: Can an AI be trained to help in this process?