🎓 Student Grade Classification Using CatBoost and XGBoost

A group project that builds multi-class classification models to predict students' grade classes (A–F) based on GPA-derived labels. The analysis uses CatBoost and XGBoost with hyperparameter tuning and model evaluation to identify patterns from student academic, demographic, and behavioral data.

---

🔧 Features

• Label generation: mapping GPA to grade class (A–F)
• Feature preprocessing and encoding of categorical data.
• Multi-class classification using:
  • CatBoost Classifier
  • XGBoost Classifier
• Hyperparameter tuning with GridSearchCV.
• Model evaluation using:
  • Confusion matrix plot
  • Classification report (accuracy, precision, recall, F1-score)

---

🧠 Concepts Used

• Supervised learning for multi-class classification
• Gradient boosting algorithms (CatBoost, XGBoost)
• GPA-based grade class mapping
• Cross-validation and hyperparameter tuning
• Evaluation metrics for multi-class performance analysis

---

👥 Group Members

• Malvin Ferdinand Tanzil
• Marcelline Cathrine Wilison
• Miecel Alicia Angel J
• William Darma Wijaya