A Data Analytics project to analyse the performance of a song on the Billboards charts done using the one Million Song Dataset.
To obtain the one million song dataset please visit : https://labrosa.ee.columbia.edu/millionsong/
The Million Song Dataset is a freely-available collection of audio features and metadata for a million contemporary popular music tracks. The dataset is maintained by Columbia University.
The models have been made using R. All the models used for analysis is present in models folder. Data preprocessing of the hd5 files downloaded from the One Million Song dataset can be done using the code found in the data preprocessing folder.
For concepts and background on the project done please read the attached pdf document.