Skip to content

The project involves using machine learning techniques, like RandomForestClassifier and MLP, to predict whether a song will be popular or not based on its acoustic features. The input consists of various acoustic and metadata features, while the output is a binary classification.

License

Notifications You must be signed in to change notification settings

adarshsankarrs/Spotify-Data-Analysis---RF-vs-MLP-Study

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

Spotify-Data-Analysis---RF-vs-MLP-Study

The project involves using machine learning techniques, like RandomForestClassifier and MLP, to predict whether a song will be popular or not based on its acoustic features. The input consists of various acoustic and metadata features, while the output is a binary classification.

We evaluate the accuracy using ROC curves and Precision-Recall curves on both MLP and RF and come to certain conclusions ,they are as follows:

For Good Performance:

If we want accurate and well-rounded results, go for the Random Forest model. It excels in precision and overall effectiveness.

For Considering Interpretability and Efficiency:

If we prioritize understanding the model or need efficient computing, think about the MLP model. We also have to be cautious about potential instability during convergence needs attention.

Our choice should match what your task needs considering the trade-offs between accuracy, stability, and interpretability, especially in the Spotify dataset context.

About

The project involves using machine learning techniques, like RandomForestClassifier and MLP, to predict whether a song will be popular or not based on its acoustic features. The input consists of various acoustic and metadata features, while the output is a binary classification.

Topics

Resources

License

Stars

Watchers

Forks

Packages

No packages published