Predicting the Likelihood of Type2 Diabetes with Random Forest Classifier

A chronic medical illness known as diabetes is defined by elevated levels of the body's natural sugar, or glucose, in the blood. Over time, numerous researchers have endeavored to establish dependable diabetes prediction models. However, the field continues to grapple with unresolved research challenges due to insufficient data sets and prediction methods. Consequently, researchers are compelled to employ machine learning and big data analytics methodologies to address these issues. This research study has analyzed two widely recognized classification models, namely Decision Tree and Logistic Regression. Further, this research study has investigated the Bagging and Boosting methods to increase the toughness of these models. Additionally, the assessment of Random Forest is considered as a part of the research investigation. The results indicate that the Random Forest algorithm yielded the most promising performance in classifying the disease risk.