This project presents a comparative analysis of Decision Tree and Naive Bayes algorithms for maternal health risk classification using the Maternal Health Risk dataset. The study evaluates model performance before and after hyperparameter optimization through tuning techniques. Performance is assessed using Confusion Matrix, Precision, Recall, F1-Score, AUC, and ROC Curve. The results provide insights into the effectiveness of both classification methods in identifying maternal health risk levels and demonstrate the impact of model optimization on predictive performance.