Billboard_Super_Hit_Song_Prediction | Billboard Hot 100 is one of the most credible record charts

Billboard_Super_Hit_Song_Prediction is a Jupyter Notebook library. Billboard_Super_Hit_Song_Prediction has no bugs, it has no vulnerabilities and it has low support. You can download it from GitHub.

Billboard Hot 100 is one of the most credible record charts in the music industry in the United States. While there are more than 75,000 albums released in the U.S. per year, only a few songs can stay on the board for a long period of time. We are curious about how these songs differ from others. Thus, the goal of this project is to uncover the secrets behind popular songs. More specifically, we would like to identify songs that pass our 20-week on-board threshold on the Billboard HOT 100 record chart. Concretely, our project aims to build a model that can correctly predict whether a Hit song will become a Super Hit based on the song's audio features and metadata extracted from Spotify. Songs that are considered as Hits are the ones that entered the Billboard HOT100 record chart (meaning that the song was once on the Billboard for at least one week); Songs that are labeled as Super Hits are the ones that remained on Billboard HOT100 for more than 20 weeks. Click on the Jupyter Notebook file to view the project. Click on this Youtube video for a brief walk-through of the project framework