Skip to content

Predicting the grammy award winners based on song popularity, musical attributes, and historical trends

Notifications You must be signed in to change notification settings

chriskeating603/grammy-predictions

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

33 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Modeling Song Popularity with Spotify and Genius Data


Interactive App

Check out my interactive app where you can explore the different musical traits of the nominees and compare your predictions to my model!

Background

I have a deep interest in audio and what attracts humans to different characteristics of songs and podcasts. I want to model those musical attributes and how those affect popularity in various ways. I brought together data from many different sources (webscraping, APIs, Spotify, Genius, Kaggle) and hope to bring a unique approach to measuring popularity and what causes it.

From that research, then we can make some predictions for the upcoming 2021 Grammy Awards based on past winners and the musical attributes of this year's nominees.


The Project

Some skills I demonstrate in this project

  • cleaning and transforming messy data
  • data modeling popularity (using regression) and genres (classification)
  • gleaning nonobvious insights based on subject matter expertise
  • webscraping and utilizing APIs
  • visualizing time series
  • getting to the "so what" - moving from the data to decisions-making (in this case, making financial bets on the Grammy Awards)

License

MIT


About

Predicting the grammy award winners based on song popularity, musical attributes, and historical trends

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages