Perbandingan Optimalisasi Hasil Klasifikasi Menggunakan Pso Pada Algoritma C.45 Dan Cart (Studikasus Prediksi Penyakit Stroke)

This study aims to compare the performance of four different classification models, namely CART, Decision Tree C4.5, and their respective versions with Particle Swarm Optimization (PSO), in the context of classification. Evaluation is conducted using four main performance metrics: accuracy, precision, recall, and Area Under Curve (AUC). The data are tested using these four models, and the results are compared to identify the most effective model in predicting the target class. The results indicate that the Decision Tree C4.5 model, especially when enhanced with PSO, consistently outperforms the CART model in terms of accuracy, precision, recall, and AUC.