<![CDATA[Kidney disease is a highly prevalent health problem that can seriously impact the quality of life of those affected. To improve diagnostic accuracy, machine learning methods are widely used to classify patient data. Class imbalance (imbalanced data) is one of the problems that often occurs in the classification process and can affect the performance of machine learning models, especially in detecting minority classes. This study aims to improve the performance of the Support Vector Machine (SVM) algorithm by applying the SMOTE (Synthetic Minority Over-sampling Tech-nique) and Grid Search methods in the data classification process. SMOTE is used to balance the class distribution by adding synthetic data to the minority class, while Grid Search is used to ob-tain optimal model parameters. The results show that the SVM model without handling data im-balance produces relatively low performance with an accuracy value of 51%, precision 17%, re-call 33%, and F1-score 23%. After applying the SMOTE method, the model performance increases significantly to 81% accuracy, 81% precision, 80% recall, and 81% F1-score. Furthermore, the ap-plication of Grid Search to the SVM + SMOTE model provides the best results with an accuracy of 84%, precision 82%, recall 81%, and F1-score 81% with an AUC value of 0,92. The findings of this study indicate that the combination of SMOTE and Grid Search is effective in improving the per-formance of the SVM algorithm in data classification. The novelty of this study demonstrates that data imbalance management and hyperparameter optimization play a crucial role in producing more accurate and optimal classification models.]]>
