Algoritma Random Forest dan Synthetic Minority Oversampling Technique (SMOTE) untuk Deteksi Diabetes

Nurussakinah, Nurussakinah
Faisal, Muhammad
Santoso, Irwan Budi

JISKa (Jurnal Informatika Sunan Kalijaga)
Vol. 10 No. 2 (2025): May 2025

Diabetes is one of the challenges in global health. Indonesia ranks 5th in the world with the highest rate of diabetes. This research uses the Random Forest algorithm for diabetes detection. The purpose of this study is to detect diabetes using the Random Forest algorithm, which provides accurate and efficient results in the early diagnosis of diabetic patients. The data used is secondary data, specifically the “Diabetes Dataset,” which consists of 952 data points and has 17 features. The test scenario in this study divides the data into three parts, namely scenario 1 (90:10 ratio), scenario 2 (70:30 ratio), and scenario 3 (50:50 ratio). In each scenario, a comparison is made between using SMOTE and not using it. The best performance results are obtained in scenario 1, which uses SMOTE, producing 97% accuracy, 100% precision, 94% recall, and an F1-score of 97%.