Evaluasi Algoritma Decision Tree dan Random Forest serta Efektivitas Feature Selection dalam Memprediksi Kesehatan Mental

Abstract

Stress has become a significant health issue in modern society, with substantial impacts such as sleep disorders and cardiovascular diseases. This study utilizes wearable devices to monitor real-time physiological data, such as heart rate and sleep patterns, to predict stress risks using machine learning algorithms, namely Decision Tree and Random Forest. The results indicate that Random Forest excels in overall accuracy for high-dimensional data, while Decision Tree demonstrates a better balance in identifying minority classes with strong Precision, Recall, and F1-Score performance. Feature selection does not significantly enhance performance but aids in computational efficiency and model interpretability. This research contributes to developing accurate and efficient stress prediction systems based on wearable devices.