For a variety of reasons, the banking industry continues to call for a more exacting predictive modeling framework. For the banking industry, it is challenging to predict credit defaulters. One of the criteria used to evaluate a loan's quality is its status, which comes after the loan application stage. Everything is not immediately visible. The loan status serves as the basis for the credit scoring model. Discovering defaulters is necessary and, ultimately, legitimate clients, credit data is reviewed with credibility using the credit score model. A model for credit rating credit data is what this study aims to produce. Many machine learning approaches are used in the development of the financial credit score model. In this research, we propose an analytical model for credit data based on machine learning classifiers. We put Min-Max normalization and linear regression together. The Jupyter notebook software suite is used to achieve the objective. The reason this model is recommended is that it delivers the most precise critical information. To forecast commercial banks loan status, and deploy a machine learning classifier.