With the development of financial technology, the traditional experience-based and single-network credit default prediction model can no longer meet the current needs. This manuscript proposes a credit default prediction model based on TabNeT-Stacking. First, use the PyTorch deep learning framework to construct an improved TabNet structure. The multi-population genetic algorithm is used to optimize the Attention Transformer automatic feature selection module. The particle swarm algorithm is used to optimize the hyperparameter selection and achieve automatic parameter search. Finally, Stacking ensemble learning is used, and the improved TabNet is used to extract features. XGBoost (eXtreme Gradient Boosting), LightGBM (Light Gradient Boosting Machine), CatBoost (Category Boosting), KNN (K-NearestNeighbor), and SVM (Support Vector Machine) are selected as the first-layer base learners, and XGBoost is used as the second-layer meta-learner. The experimental results show that compared with original models, the credit default prediction model proposed in this manuscript outperforms the comparison models in terms of accuracy, precision, recall, F1 score, and AUC (Area Under the Curve) of credit default prediction results.

Under the rapid evolution of financial technology, traditional credit risk management paradigms relying on expert experience and singular algorithmic architectures have proven inadequate in addressing complex decision-making demands arising from dynamically correlated multidimensional risk factors and heterogeneous data fusion. This manuscript proposes an enhanced credit rating model based on an improved TabNet framework. First, the Kaggle “Give Me Some Credit” dataset undergoes preprocessing, including data balancing and partitioning into training, testing, and validation sets. Subsequently, the model architecture is refined through the integration of a multi-head attention mechanism to extract both global and local feature representations. Bayesian optimization is then employed to accelerate hyperparameter selection and automate a parameter search for TabNet. To further enhance classification and predictive performance, a stacked ensemble learning approach is implemented: the improved TabNet serves as the feature extractor, while XGBoost (Extreme Gradient Boosting), LightGBM (Light Gradient Boosting Machine), CatBoost (Categorical Boosting), KNN (K-Nearest Neighbors), and SVM (Support Vector Machine) are selected as base learners in the first layer, with XGBoost acting as the meta-learner in the second layer. The experimental results demonstrate that the proposed TabNet-based credit rating model outperforms benchmark models across multiple metrics, including accuracy, precision, recall, F1-score, AUC (Area Under the Curve), and KS (Kolmogorov–Smirnov statistic).