Credit Rating Model Based on Improved TabNet

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 a...

Full description

Saved in:
Bibliographic Details
Main Authors: Shijie Wang, Xueyong Zhang
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/9/1473
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850137659187396608
author Shijie Wang
Xueyong Zhang
author_facet Shijie Wang
Xueyong Zhang
author_sort Shijie Wang
collection DOAJ
description 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).
format Article
id doaj-art-ec1e31f70ef74c548a7a5613da1b2e7d
institution OA Journals
issn 2227-7390
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-ec1e31f70ef74c548a7a5613da1b2e7d2025-08-20T02:30:46ZengMDPI AGMathematics2227-73902025-04-01139147310.3390/math13091473Credit Rating Model Based on Improved TabNetShijie Wang0Xueyong Zhang1School of Finance, Central University of Finance and Economics, Beijing 102206, ChinaSchool of Finance, Central University of Finance and Economics, Beijing 102206, ChinaUnder 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).https://www.mdpi.com/2227-7390/13/9/1473TabNetstackingcredit ratingcredit risk
spellingShingle Shijie Wang
Xueyong Zhang
Credit Rating Model Based on Improved TabNet
Mathematics
TabNet
stacking
credit rating
credit risk
title Credit Rating Model Based on Improved TabNet
title_full Credit Rating Model Based on Improved TabNet
title_fullStr Credit Rating Model Based on Improved TabNet
title_full_unstemmed Credit Rating Model Based on Improved TabNet
title_short Credit Rating Model Based on Improved TabNet
title_sort credit rating model based on improved tabnet
topic TabNet
stacking
credit rating
credit risk
url https://www.mdpi.com/2227-7390/13/9/1473
work_keys_str_mv AT shijiewang creditratingmodelbasedonimprovedtabnet
AT xueyongzhang creditratingmodelbasedonimprovedtabnet