Implementation of Random Forest Model with Hyperparameter Tuning for Diabetes Mellitus Classification

This research aims to classify Diabetes Mellitus (DM) using the Random Forest (RF) model by exploring feature selection techniques and hyperparameter tuning. DM is a metabolic disorder in the body due to bodily incompetence produces or delivers the finished hormone insulin causes blood sugar levels to rise above normal. High sugar levels in the bloodstream can cause heart disease, stroke, kidney disease, blindness, nerve damage in the feet, etc. So, diabetes must be detected as early as possible so that sufferers can receive early treatment. One of the machine learning models that can be used to create a diabetes detection model is the random forest (RF) model. The results from RF will be compared with other machine learning models such as K-Nearest Neighbors (KNN), and Extreme Gradient Boosting (XGBoost). The comparison results show that RF model is better and achieves the highest accuracy with an accuracy value of 97%.