Comparative Analysis of Machine Learning Models for Diabetes Prediction

This paper aims at comparing performance of various machine learning models for the task of predicting diabetes using one of the public datasets. The research assesses the big data analysis in the determination of the possibilities of risk of diabetes and the preferred models of Logistic Regression and KNearest Neighbors (KNN). Performance measures including accuracy, precision and recall were used in assessing the performance of the two models. The study do reveals the high level of potential of both the models yet reveals that Logistic Regression just edges a bit ahead of KNN in terms of accuracy and precision. These results show the potential of using machine learning in hospital diagnosis and specifically in diagnosis of Chronic diseases such as diabetics.