Credit Risk Model: Research on Credit Risk Categorization model using XGBoost

Credit Risk Model: Research on Credit Risk Categorization model using XGBoost

Puneet Singh1, Shubha Mishra2, Gargi Porwal3, Prakhar Saxena4, Rishabh Tripathi5

1Bachelor of Technology in Computer Science Engineering, Babu Banarasi Das Institute of Technology and Management, Lucknow

2Assistant Professor, Computer Science Engineering, Babu Banarasi Das Institute of Technology and Management, Lucknow

3Bachelor of Technology in Computer Science Engineering, Babu Banarasi Das Institute of Technology and Management, Lucknow

4Bachelor of Technology in Computer Science Engineering, Babu Banarasi Das Institute of Technology and Management, Lucknow

5Bachelor of Technology in Computer Science Engineering, Babu Banarasi Das Institute of Technology and Management, Lucknow

---------------------------------------------------------------------***---------------------------------------------------------------------

Abstract - Machine Learning is a subset of Artificial Intelligence technology that enables systems to learn and make decisions on their own. These systems can make accurate decisions by analyzing datasets and information without the need for explicit programming. This paper mainly introduces the application of machine learning algorithm (XGBoost) in credit risk assessment in the financial industry. Credit risk assessment is a significant challenge for banks to assess credit worthiness among many applicants and plays a very crucial role in the profitability of banks.

Our research paper addresses the limitations and complexities in the current models in the market that lack interpretability and transparency. The methodology section introduces the application of the random forest model in financial quantification, including the model principle, feature importance calculation and experimental design. Utilizing the dataset comprising of more than one lakh users from the CIBIL and other banks and then through the exploratory data analysis, feature selection and model construction of the credit risk prediction dataset, the construction and evaluation process of the CRM model is demonstrated.

 Finally, the performance of the XGBoost model after hyperparameter tuning is evaluated and compared with other models to demonstrate its advantages and applicability in financial quantification.

Key Words: XGBoost, Machine Learning, Credit Risk Model, Random Forest