Measuring the Significance of the Geographic Flow of Music

In previous work, our results suggested that some cities tend to be ahead of others in their musical preferences. We concluded that work by noting that to properly test this claim, we would try to exploit the leader-follower relationships that we identified to make predictions. Here we present the results of our predictive evaluation. We find that information on the past musical preferences in other cities allows a linear model to improve its predictions by approx. 5% over a simple baseline. This suggests that at best, the previously found leader-follower relationships are rather weak. I. REINTERPRETING THE PROBLEM OF FINDING LEADER-FOLLOWER RELATIONSHIPS AS A PREDICTION