This project addresses the problem of class imbalance in classification tasks using Python-based machine learning techniques. Real-world examples include fraud detection, rare disease prediction, and more.

• Data visualization and analysis
• Handling imbalance using:
  • Oversampling (Random, SMOTE, ADASYN)
  • Undersampling
• Model training using:
  • Random Forest
  • XGBoost
• Evaluation with metrics suited for imbalance:
  • F1-score, ROC-AUC, Confusion Matrix

• Python 3.8+
• pandas, numpy, matplotlib, seaborn
• scikit-learn, imbalanced-learn
• xgboost

• notebooks/: Jupyter Notebook implementation
• src/: Python scripts for data handling and modeling
• outputs/: Generated charts and results
• report/: Final PDF project report

git clone https://github.com/your-username/classification-imbalanced-data-ml.git
cd classification-imbalanced-data-ml
pip install -r requirements.txt