Abstract: Extending credit to individuals is necessary for markets and society to function smoothly. Estimating the probability that an individual would default on their loan, is useful for banks to decide whether to sanction a loan to the individual or not. We introduce an effective prediction technique that helps the banker to predict the credit risk for customers who have applied for loan. A prototype is described in the paper which can be used by the organizations for making the correct or right decision for approve or reject the request for loan of the customers. The paper uses three different models (SVM Model, Random Forest Network and Tree Model for Genetic Algorithm) and the Ensemble Model, which combines these three models and analyses the credit risk for optimum results.

Keywords: Ensemble, Prediction, Loan, Random forest.