Paper Title
COMPARATIVE ANALYSIS OF MACHINE LEARNING MODELS FOR DIABETES PREDICTION

Abstract
Diabetes Mellitus is a chronic medical disorder which impacts the health of the world. One of the labels for diabetes is the silent killer of the human body. Timely diagnosis of diabetes risk can allow for prompt action and individualized healthcare treatment. With the aid of machine learning, more precise predictions in the healthcare industry can be made. It's an area of study devoted to making computers capable of learning and improving themselves without the need for explicit programming. In our paper, we applied eleven machine learning techniques in the Pima Indian diabetes dataset to categorize individuals into either diabetic or non-diabetic category. We evaluated each model’s performance through the use of eight key metrics: F1 Score, Accuracy, Classification Error, AUC Score, Precision, MCC Score, Recall, and Balanced Accuracy. Our experimental results highlight that Random Forest outperformed other techniques when compared on above metrics, demonstrating its potential utility for diabetes diagnosis. Keywords - Diabetes Mellitus, Machine Learning, Python