Media and Entertainment Client

Model – Research Response:

Utilize song and artist-level local & national data from research conducted by stations, radio play, song surveys and various, on-demand streaming and chart rankings  to create a “consensus, data driven” research response estimate.

Use Cases & Benefits:

  • Provide more stable music data that is less subject to “wobbling” from test to test
  • Provide research information for more songs each week
  • Provide research data when station-level research is not available

Model – Song Popularity

Utilize song and artist-level local & national data from research conducted by stations, radio play, song surveys and various, on-demand streaming and chart rankings  to predict song popularity today, and in the future, to derive recommended play lists tailored to specific user profiles and geographies.

Use Cases & Benefits:

  • Predict the song “lifecycle” curve to supplement gut-feel with data.
  • Identify what are the best songs to add to rotations.
  • Identify which songs to move into a power position.
  • Get the most out of a popular song and not move a song out of rotation too soon. Identify which songs should be moved out of rotation.

Model – Early Indicator

Predict early in the song lifecycle that a song will be a hit.

  • SPSS Modeler was used in all exploratory data analysis, data wrangling and the creation of models in the projects.