Performance Evaluation of Advanced Classification Models Combined with Feature Selection for Credit Risk Performance

Abstract

In this study, we propose an advanced methodology utilizing machine learning models for predicting home equity credit risk on a real-world dataset. Traditional credit risk models often rely on outdated statistical methods that fail to capture complex, non-linear relationships in data, resulting in suboptimal accuracy and limited interpretability. Furthermore, existing models lack transparency, making it difficult for stakeholders to understand and act on the predictions. To address these issues, we employ state-of-the-art machine learning algorithms such as Decision Trees, AdaBoost, Support Vector Machine (SVM), Neural Networks, and Random Forest, along with feature selection techniques like Boruta and Principal Component Analysis (PCA) to enhance both accuracy and explainability. Our approach aims to provide improved credit risk assessment tools, offering better interpretability for loan companies, regulators, and applicants, while ensuring robust performance. The results demonstrate that our proposed models outperform traditional methods and offer actionable insights for stakeholders, enhancing decision-making processes.