<![CDATA[Obesity is a growing health concern that is closely associated with various chronic diseases. Machine learning has been widely applied to classify obesity levels, yet most studies focus on improving predictive performance rather than identifying the features contributing to classification outcomes. This study aims to analyze the determining factors of obesity levels using Feature Importance in a Random Forest model. The research utilized the Estimation of Obesity Levels Based on Eating Habits and Physical Condition dataset from the UCI Machine Learning Repository. After preprocessing, 2,087 records were analyzed. Hyperparameter tuning was performed using GridSearchCV, and model performance was evaluated using Accuracy, Precision, Recall, and F1-Score. The optimized Random Forest achieved an Accuracy of 94.26%, Precision of 94.60%, Recall of 94.26%, and F1-Score of 94.34%. Feature Importance analysis identified Weight as the most influential feature, followed by Age, FCVC, Height, and Gender. The results demonstrate that Random Forest not only provides high classification performance but also helps identify the features that contribute most to obesity level classification.]]>
Copyrights © 2026
