MTH221-FINAL-PROJECT-ipynb-is-working-

This study investigates the efficacy of various ma- chine learning algorithms for music genre classification. We used a dataset of 114,000 music tracks with diverse features. Our approach included data preprocessing, hyperparameter tuning, and evaluating multiple models including Random Forest, SVM, Decision Tree, Voting Classifier, Stacking Classifier, and XGBoost Classifier. The results demonstrate that ensemble methods, par- ticularly the Stacking and XGBoost classifiers, outperform single models with an accuracy of 99%.