Hit Song Science

From Wikipedia, the free encyclopedia

Hit Song Science is a term coined by Mike McCready and trademarked by the company he co-founded, Polyphonic HMI. It concerns the possibility of predicting whether a song will be a hit, before its distribution using automated means such as machine learning software.

Scientific background[edit]

The scientific nature of Hit Song Science is a subject of debate in the music information retrieval (MIR) community. Early studies claimed that using machine learning techniques could capture some information from audio signals and lyrics that would explain[1] popularity. However, a larger-scale evaluation[2] contradicts the claims of “Hit Song Science”, i.e. that the popularity of a music title can be learned effectively from known audio features. Many other reasons, including the well-known cumulative advantage or preferential attachment effects deeply contradicts[3] the possibility of practical applications. Nevertheless, automatic prediction techniques are the basis of hit counseling businesses (HSS Technology). Recent work by Herremans et al. [4] has shown that audio features can indeed be used to outperform a random oracle when predicting top 10 versus top 30-40 hits.[5]

Commercial applications[edit]

A technology proposing to exploit Hit Song Science was introduced in 2003 by an artificial intelligence company out of Barcelona, Spain, called Polyphonic HMI. Polyphonic HMI has since spun off a new Delaware C corporation, Music Intelligence Solutions, Inc., which used to run uPlaya, a site geared toward music professionals. In 2006 however one of the company's founders, Mike McCready left to pursue another direction in the digital music space. The idea of Hit Song Science has generated response from many in the music industry, including Chuck D,[6] Robert Lamm, Stratton Leopold,[7] Gregg Scholl of The Orchard,[8] and officials at The Sync Agency[9] as well as Blue Infinity Music. Prior to McCready's departure, Hit Song Science was profiled by NBC,[10] BBC[11] and various major news outlets. The plotline of an episode of "Numb3rs"[12] was inspired by the technology. Music Intelligence Solutions, Inc., is using Hit Song Science as a basis for several contests done in partnership with organizations such as AllHipHop.com, Urban Latino and American Songwriter magazine, and claims to have predicted the commercial success of Norah Jones's debut album, Come Away with Me, (which won a Grammy for Best Album) and Ben Novak's debut single, "Turn Your Car Around", which reached the number 12 spot in the UK Top 40 charts.[13]

Similar technologies are now emerging with companies such as Mixcloud, MusicXray, and BandMetrics who are using their technologies. Mixcloud is working with Queen Mary Technologies.


  1. ^ Dhanaraj, R., and Logan, B. Automatic Prediction of Hit Songs, Proc. of Ismir 2005, London, UK
  2. ^ Pachet, F. and Roy, P. (2008) Hit Song Science is Not Yet a Science. Proceedings of Ismir 2008, pages 355-360, Philadelphia, USA
  3. ^ Pachet, F. (2011) Hit Song Science. [1] In Tao, Tzanetakis & Ogihara, editor, Music Data Mining, CRC Press/Chapman Hall
  4. ^ Herremans, D., Martens, D., & Sörensen, K. (2014). "Dance hit song prediction" (PDF). Journal of New Music Research. 43 (3): 291–302. doi:10.1080/09298215.2014.881888. S2CID 51948760.{{cite journal}}: CS1 maint: multiple names: authors list (link)
  5. ^ Vice Magazine: A Machine Successfully Predicted the Hit Dance Songs of 2015
  6. ^ XXLmag.com: Chuck D and uPlaya Analyze Hit Songs
  7. ^ Stratton Leopold to Advisory Board
  8. ^ Music Intelligence Solutions Partners with The Orchard
  9. ^ Music Intelligence Solutions Partners with The Sync Agency
  10. ^ NBC Network News Feature on uPlaya
  11. ^ BBC News Report
  12. ^ Episode of "Numb3rs" Inspired by Hit Song Science
  13. ^ "Ben Novak's debut single enters the UK Top 40 chart at number 12". Archived from the original on 2009-09-07. Retrieved 2009-08-31.