Hit Song Science (HSS)
Have you heard of this? I first saw this in an article in the Guardian, a newspaper in the UK. It mentioned that the entire music industry was using a program developed by Polyphonic HMI in Spain to predict hit records. It compares songs to a database containing 30 years worth of Billboard hit singles, 3.5 million tunes in all, and isolates and separates 20 aspects of song construction including melody, harmony, chord progression, beat, tempo and pitch. It then identifies and maps recurrent patterns in a song, compares it to past hits, and tells you in 24 hours if you have a #1 on your hands. Score a high enough rating and watch your phone calls suddenly being returned by the Ohs & Ahs, I mean A&R.
It's all about the clusters. Musical tastes fall into some 50 different clusters according to the numbers. Some U2 songs are in the same cluster as Beethoven, while spandex ultra rocker Van Halen sits right alongside MOR piano babe Vanessa Carlton. Whether it was Van Hagar or Gary Cherone did not matter. Shocking.
Tracie Reed of HSS is quoted, "We promise 100% success rate for songs released rather than the usual 20%. Which makes it a justifiable [$4,800] investment."
Sounds kind of boring but how much different is it than today's BDS vs. Soundscan research game?