The chronic kidney failure is a extreme fitness issue and if not detected and handled on the early degrees, it can be very lethal. Hence the essential goal of this paper is to increase a dependable system learning version which predicts the CKD with a high accuracy price. The CKD statistics set is downloaded from the famous UCI ML repository but it suffers from a variety of lacking values. To deal with the lacking values KNN Imputation is used. Feature selection is likewise completed with the assist of information benefit because the dataset is massive and consequently the fee of modelling can be very excessive. Various other pre-processing steps like label encoding and Min-max normalization is executed to obtain a clean dataset. After pre-processing, diverse ML algorithms like logistic regression, naïve bayes, synthetic neural network and random wooded area are implemented and their performances are in comparison with the assist of diverse overall performance metrics. A hybrid of Random Forest and Adaboost algorithm is proposed and it achieves a higher accuracy when in comparison to the opposite person element models and subsequently it may be proved that the proposed hybrid version is an awful lot better and accurate in diagnosing CKD. goal of this paper is to increase a dependable system learning version which predicts the CKD with a high accuracy price. The CKD statistics set is downloaded from the famous UCI ML repository but it suffers from a variety of lacking values. To deal with the lacking values KNN Imputation is used. Feature selection is likewise completed with the assist of information benefit because the dataset is massive and consequently the fee of modelling can be very excessive. Various other pre-processing steps like label encoding and Min-max normalization is executed to obtain a clean dataset. After pre-processing, diverse ML algorithms like logistic regression, naïve bayes, synthetic neural network and random wooded area are implemented and their performances are in comparison with the assist of diverse overall performance metrics. A hybrid of Random Forest and Adaboost algorithm is proposed and it achieves