SMOTE-SVM for Handling Imbalanced Data in Obesity Classification

Obesity is a significant health issue associated with various chronic diseases, making its early classification critical for effective interventions. This study investigates the performance of Support Vector Machine (SVM) models with Radial Basis Function (RBF) and Linear kernels on imbalanced obesity datasets. To address data imbalance, Synthetic Minority Over-sampling Technique (SMOTE) and Random Undersampling (RUS) were applied. The results reveal that balancing techniques significantly enhance classification performance, with the Linear model achieving the highest accuracy of 96.54% when balanced using SMOTE. However, limitations include reduced recall for minority classes and potential overfitting risks. These findings underscore the importance of balancing techniques in health data classification and offer insights for further optimizing model performance. The study highlights the need for advanced data balancing strategies to improve predictive accuracy and equity across all classes.