Chronic kidney disease (CKD) is an increasing medical issue that declines the productivity of renal capacities and subsequently damages the kidneys. CKD is very common nowadays; cardiovascular infection and end-stage renal illness are two life threatening diseases that can be caused as after-effects of CKD. These are conceivably preventable through early recognizable conditions and treatment of people who are in danger. The expectation of medical problems is a very troublesome assignment. CKD is particularly one of the most lethal diseases in the clinical field. Before it becomes too late to recognize CKD forecast, to get rid of risks, the prediction of risk factor is a major necessary step in the immediate stage. In this research work six algorithms such as Naïve Bayes, Random forest, Simple logistic regression, Decision Stump, Linear regression model, simple linear regression model is used to predict the risk factors of CKD. Considering the orderly execution and investigations of these strategies, six algorithms give a superior and quicker characterization execution. Six individual algorithms are applied to the dataset and the best outcomes have been acquired through the classification of predicting risk factors.