<![CDATA[Obesity is a condition caused by an imbalance between energy intake and expenditure, characterized by excessive fat accumulation in the body. Obesity is influenced by four factors, namely genetics, economics, lack of activity, and diet. The purpose of this study is to analyze the effectiveness of the SMOTE method in improving the accuracy of classification in the Support Vector Machine method and to compare the accuracy of the Support Vector Machine method with the SMOTE and non-SMOTE techniques on adolescent obesity data. The dataset used was obtained from the Kaggle website, which contained 2,111 records. The model evaluation used a confusion matrix with accuracy, precision, recall, and F1-score measurements and used 80:20 data splitting. The results showed that the SVM model using Smote performed well with an accuracy of 88% for Linear SVM, 82% for RBF SVM, and 93% for Polynomial SVM, while the SVM model without Smote achieved an accuracy of 88% for Linear SVM, 79% for RBF SVM, and 91% for Polynomial SVM. The best classification model was then implemented into a Streamlit-based web application to facilitate the process of automatically predicting obesity levels, thereby helping to raise awareness of the potential risks of obesity.]]>
Copyrights © 2025
