1. Harnessing Advanced Machine Learning Models for Credit Outlook Analysis.
- Author
-
Malhotra, Rashmi, Malhotra, D. K., and Malhotra, Kunal
- Subjects
MACHINE learning ,BANKING industry ,RANDOM forest algorithms ,FINANCE companies ,FINANCIAL services industry - Abstract
This article extends previous research by Malhotra, Malhotra, and Malhotra (2024) exploring advanced machine learning models to predict the credit outlook for banking and nonbanking finance companies. The authors compare the predictive performance of five models, which include XGBoost, random forest classifier, gradient boost, AdaBoost using decision tree classifier, and AdaBoost using support vector classifier. The primary goal is to enhance predictive accuracy and detect potential distress signals early. Our findings reveal XGBoost as the standout performer, demonstrating superior accuracy across all credit outlooks while minimizing false positives. Gradient boosting also performs well, showing promise for accurate prediction. Cross-validation ensures model generalizability, with gradient boosting and SVM consistently performing well. The results emphasize the potential of machine learning models in accurately categorizing finance companies based on credit outlooks. Furthermore, the superiority of gradient boosting suggests its integration into operational frameworks for enhanced credit risk assessment, promoting stability within the financial industry. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF