Chronic Kidney Disease (CKD) is a chronic renal failure condition that is one of the most serious and rapidly spreading diseases in today’s world. Each kidney is composed of several filtrating units called Nephrons. It is difficult to predict renal failure at an early stage because there are no specific symptoms. This can have long-term consequences for the patient’s health and even result in death. People who have type 2 diabetes or high blood pressure have the highest risk for renal failure. The objective of this paper is to analyze and evaluate the performance of a few existing predictive models for Chronic Kidney Disease (CKD) utilizing different Machine Learning Classification Algorithms. A powerful Machine Learning approach that is frequently applied to prediction is Classification. Different classifiers such as Random Forest, Decision Tree, K-Nearest Neighbour, Ada Boosting, Gradient Boosting, and Naive Bayes are used for the classification of CKD. Out of all the classifiers Random Forest and Gradient Boosting produced the best accuracy result when compared with other classifiers. A comparison of the accuracy score along with the confusion matrix to identify correct and incorrect features is presented to detect the optimal model.