🤖 AI Summary
Traditional credit risk models face performance bottlenecks due to high-dimensional features, rare default events, and severe class imbalance across multi-level credit ratings. To address these challenges, this paper proposes an interpretable credit risk prediction framework integrating LASSO-based feature selection, Error-Correcting Output Codes (ECOC), and meta-learning. The framework unifies supervised (e.g., XGBoost, Random Forest), unsupervised, and deep learning base models; ECOC mitigates multi-class imbalance, LASSO reduces dimensionality and enhances generalization, and permutation-based feature importance quantifies critical risk drivers. Experiments on credit rating data from 2,029 U.S. public firms demonstrate significant improvements in both default probability estimation and credit migration classification accuracy. The method achieves strong discriminative power while preserving model transparency and interpretability, establishing a novel paradigm for financial risk management that balances robustness and explainability.
📝 Abstract
Effective credit risk management is fundamental to financial decision-making, necessitating robust models for default probability prediction and financial entity classification. Traditional machine learning approaches face significant challenges when confronted with high-dimensional data, limited interpretability, rare event detection, and multi-class imbalance problems in risk assessment. This research proposes a comprehensive meta-learning framework that synthesizes multiple complementary models: supervised learning algorithms, including XGBoost, Random Forest, Support Vector Machine, and Decision Tree; unsupervised methods such as K-Nearest Neighbors; deep learning architectures like Multilayer Perceptron; alongside LASSO regularization for feature selection and dimensionality reduction; and Error-Correcting Output Codes as a meta-classifier for handling imbalanced multi-class problems. We implement Permutation Feature Importance analysis for each prediction class across all constituent models to enhance model transparency. Our framework aims to optimize predictive performance while providing a more holistic approach to credit risk assessment. This research contributes to the development of more accurate and reliable computational models for strategic financial decision support by addressing three fundamental challenges in credit risk modeling. The empirical validation of our approach involves an analysis of the Corporate Credit Ratings dataset with credit ratings for 2,029 publicly listed US companies. Results demonstrate that our meta-learning framework significantly enhances the accuracy of financial entity classification regarding credit rating migrations (upgrades and downgrades) and default probability estimation.