The objective of the current research is to implement the Random forest approach to predict chronic kidney disease. One of the main chronic ailments is kidney disease. It is extremely cost-effective to identify the problem at an early stage. As the problem is extremely cost-effective, there is a constant concern of the global economic pressure. The aim of the research work is to create a practical model which will be able to predict the disease accurately at an early stage. The initial system relying on the K Nearest Neighbor KNN classification approach. The model as a whole suffers from scalability as does the data, as well as the It suffers from overfitting and poor performance on selection and tuned data. The Random forest approach is an improvement over the KNN model. The Random forest model has proven itself to be better than the KNN approach, and shows l prediction accuracy on chronic kidney disease case. The research work shows how advancement in machine learning could improve prediction on the specified ailment. Aspects like feature projection, data preprocessing data, and alternate ensemble learning methods could be used in future work to improve. Such results but point towards the essential need of Indic.