A serious condition that can last a lifetime, Chronic Kidney Disease (CKD) is brought on by either impaired kidney function or kidney cancer. It is possible to stop or limit the advancement of this chronic illness to the point when a patient's sole options for survival are dialysis or surgery. Chronic kidney disease (CKD) is caused by illnesses that impair and diminish kidneys' ability to maintain and human health. Consequently, kidney disease must be taken seriously from the very beginning. The chance that this will occur can be raised with early detection and suitable therapy. This study has investigated the potential of a number of machine learning techniques, including eXtreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM) and Logistic Regression (LR) for early CKD diagnosis. The performance of every classification algorithm was encouraging. The Decision Tree and Support Vector Machine achieved an accuracy of 98.61% and 97.22% for all measures respectively outperforming all other applied techniques.