<![CDATA[Diabetes is a chronic disease characterized by high blood glucose levels due to the body's inability to produce or use insulin effectively. This disease is one of the serious global health problems, and it has a significant impact; therefore, early detection is very important. Efforts to overcome this challenge can be made by applying machine learning, which provides a new and effective approach. This study aims to predict diabetes with a higher accuracy level through the Ensemble Learning Soft Voting method. In addition, the data balancing technique using SMOTE is applied to overcome the problem of imbalance in the data set. This study also compares various classification models using Machine Learning algorithms, namely LightGBM, XGBoost, and Random Forest. The test results show that the Random Forest model achieves the highest level of accuracy at 97.20%. In comparison, the Ensemble Learning Soft Voting method that combines the three algorithms has increased the accuracy to 97.74%. This Ensemble Learning approach has proven effective in significantly improving predictions and performing better than a single model.]]>
Copyrights © 2025
