Skip to content

catalinamunoz/CS305-Module-5

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 

Repository files navigation

CS305-Module-5

CS305 group assignment

Bop or Flop? A Data-Driven Approach to Predicting Hit Music

This research will explore the use of Billboard and Spotify to predict the success of songs. Billboard will be used to identify the Top 100 songs each year from 1980 - 2022. The Spotify Web API in R will be used to extract audio features of songs. These features include danceability, acousticness, energy, liveness, loudness, tempo, duration, speechiness, and valence. Using these two platforms, a dataset of thousands of “hit” and “non hit” songs will be collected, where a hit is defined by a song that graces the Year-End Hot 100. The goal of this project is to use the insights provided by Billboard and Spotify to identify the audio features that contribute the most to song success. Machine Learning will be implemented to estimate models that predict when a song will be a hit. Using cross-validated machine learning models, variable importance will be explored to elucidate what song features are most influential to a song making the Year-End Hot 100.

License

This project is licensed under the MIT License.

Project Modules

I can do the resources module, data collecting or error control.

About

No description, website, or topics provided.

Resources

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •