Nowadays there are numerous risks associated with bank loans, especially with banks reducing their capital losses. Risk estimation and measurement of defaults are critical. Banks retain large quantities of data relating to consumer conduct on which they are unable to draw a decision whether a claimant may or may not be defaulting. Descriptive analytics can let a company know what has been in the past, leveraging the stored data to provide you with past analysis. Past actions that help them make statistical decisions using empirical evidence need to be learned. Data Mining is a capable field of data processing aimed at collecting valuable information from a large number of complex data sets. In this paper, you can help to classify the correct client by using statistical models. Using historical data from the bank's client, you need to assess the factors influencing credit risk, establish measures to reduce the acquisition risk, and analyze the project's financial worth. For the prototype data set for estimation, the final model is used and the experimental findings show the usefulness of the constructed model.