Immersion's data scientists first analyzed the predictive ability of self-reported "liking" of songs. Participants reported that they "liked" familiar songs more than unfamiliar ones with a nearly perfect correlation of 0.87. This is how hits are made: the more people hear a song the more they think it is good. Remember the song Macarena? It was a breakout hit in 1996. But, by 2002, VH1 ranked Macarena as the number one "awesomely bad" one-hit wonder. (I bet you the Macarena chorus is playing in your head right now).
For music people had not heard before, self-reported "liking" had zero predictive power. "Liking" simply does not predict hits for new music. If it did, music distribution platforms would only need to ask people what to play.
What about brain activity? A combination of neurologic measures from the Immersion platform, including a song's average immersion (Value Score), its peak moments, and the number of neurologic 'superfans' for the song, predicted hits with 83% accuracy. Put differently, Value Measurement correctly identified 10 of the 12 hit songs that Pandora gave us using only neurologic data.
To ensure that our hit predictions were not just due to random chance, we also predicted other market measures of hits, including the number of plays of each song and the number of days the song had been on Pandora's platform. Song plays were positively correlated with a song's average Value Score (0.23) and peak moments (0.39), and negatively related to low points of value (-0.20). Self-reported “liking” was uncorrelated song plays. The number of days the song was on the Pandora platform was highly correlated with its average Value Score (0.45) and the number of neurologic superfans (0.38) and a negatively associated with low value (-0.26). Value Measurement predicts the hits when self-report cannot.
We analyzed the data to measure how an increase in value drives additional streams. The analysis showed that a 1% increase in value would generate 53% more streams. This means that if a song was moderately successful with 200,000 listens but had been edited to increase its value 5%, it would gain 530,00 more streams. This would move it from "just OK" to a legitimate hit with over 700,000 listens. Then the familiarity effect takes over and the song tops the charts. That is the impact of neurologic value on market responses.
