Identifying what genre a particular song belongs to has been a cakewalk for humans. Can we train the machines do this job for us? With this motivation in mind, we used Machine Learning as a tool for implementing this task of genre identification. In this project we have explored methods for exploratory data analysis, feature selection, hyperparameter optimization, and eventual implementation of several algorithms for classification.
All our codes for the random forest classifier, PCA and the Bayesian optimization can be found in the code subdirectory. The results of PCA have been stored in the images subdirectory. In the research subdirectory you may find the Stanford paper we referred to in the course of our project.
This is a project on which Arunabh, Sucheta and I worked on for our course CS419- Introduction to Machine Learning, here at IIT Bombay.