A Robust Approach to Credit Scoring with Deep Learning and Embedded Methods
Received: 11 June 2025 | Revised: 18 September 2025 | Accepted: 27 September 2025 | Online: 10 October 2025
Corresponding author: Long Quoc Tran
Abstract
Credit scoring is essential for financial institutions to assess loan risk before making credit-granting decisions. Artificial Ιntelligence (AI) models are often applied to automate processes that support these organizations in decision-making. However, credit data is usually large and contains noisy or excessive features, which can degrade model performance and lead to inaccurate predictions. In this situation, feature selection is one of the most effective methods for improving model efficiency, as it identifies the most relevant attributes while reducing dimensionality and computational cost. This study proposes a robust pipeline that integrates an embedded feature selection method, either Lasso or Elastic Net, with deep learning models to enhance credit scoring performance. The proposed method was tested on five widely used financial datasets: the Credit Card database, the Australian Credit Approval dataset, the German Credit Data dataset, the Japanese Credit Screening dataset, and the Thomas Credit Risk dataset. The comparison results show that the proposed hybrid approach outperforms both the baseline methods and PCA-based feature selection in improving credit risk assessment.
Keywords:
credit scoring, feature selection, deep learning, embedded methodsDownloads
References
K. Svirydzenka, “Introducing a New Broad-based Index of Financial Development,” IMF Working Papers, vol. 16, no. 05, 2016. DOI: https://doi.org/10.5089/9781513583709.001
J. Ha, M. A. Kose, and F. Ohnsorge, Inflation in Emerging and Developing Economies: Evolution, Drivers, and Policies. World Bank Publications, 2019. DOI: https://doi.org/10.1596/1813-9450-8761
M. A. Faheem, ''AI-Driven Risk Assessment Models: Revolutionizing Credit Scoring and Default Prediction.'' Unpublished, 2021.
R. Hlongwane, K. K. K. M. Ramaboa, and W. Mongwe, ''Enhancing credit scoring accuracy with a comprehensive evaluation of alternative data,'' PLOS ONE, vol. 19, no. 5, May 2024, Art. no. e0303566. DOI: https://doi.org/10.1371/journal.pone.0303566
S. Bi and W. Bao, ''Innovative Application of Artificial Intelligence Technology in Bank Credit Risk Management,'' International Journal of Global Economics and Management, vol. 2, no. 3, pp. 76–81, Apr. 2024. DOI: https://doi.org/10.62051/IJGEM.v2n3.08
E. Dumitrescu, S. Hué, C. Hurlin, and S. Tokpavi, ''Machine learning for credit scoring: Improving logistic regression with non-linear decision-tree effects,'' European Journal of Operational Research, vol. 297, no. 3, pp. 1178–1192, Mar. 2022. DOI: https://doi.org/10.1016/j.ejor.2021.06.053
S. Mestiri, ''Credit scoring using machine learning and deep Learning-Based models,'' Data Science in Finance and Economics, vol. 4, no. 2, pp. 236–248, 2024. DOI: https://doi.org/10.3934/DSFE.2024009
K. Tong, Z. Han, Y. Shen, Y. Long, and Y. Wei, ''An Integrated Machine Learning and Deep Learning Framework for Credit Card Approval Prediction,'' in 2024 IEEE 6th International Conference on Power, Intelligent Computing and Systems (ICPICS), Shenyang, China, July 2024, pp. 853–858. DOI: https://doi.org/10.1109/ICPICS62053.2024.10795883
Y. E. Gür, M. Toğaçar, and B. Solak, ''Integration of CNN Models and Machine Learning Methods in Credit Score Classification: 2D Image Transformation and Feature Extraction,'' Computational Economics, vol. 65, no. 5, pp. 2991–3035, May 2025. DOI: https://doi.org/10.1007/s10614-025-10893-5
B. Alshawi, ''Utilizing GANs for Credit Card Fraud Detection: A Comparison of Supervised Learning Algorithms,'' Engineering, Technology & Applied Science Research, vol. 13, no. 6, pp. 12264–12270, Dec. 2023. DOI: https://doi.org/10.48084/etasr.6434
J. Laborda and S. Ryoo, ''Feature Selection in a Credit Scoring Model,'' Mathematics, vol. 9, no. 7, Mar. 2021, Art. no. 746. DOI: https://doi.org/10.3390/math9070746
O. Koc, O. Ugur, and A. S. Kestel, "The Impact of Feature Selection and Transformation on Machine Learning Methods in Determining the Credit Scoring." arXiv, 2023.
A. B. Buriro and S. Kumar, ''The Fisher Component-based Feature Selection Method,'' Engineering, Technology & Applied Science Research, vol. 12, no. 4, pp. 9023–9027, Aug. 2022. DOI: https://doi.org/10.48084/etasr.5137
Y. El Touati, J. B. Slimane, and T. Saidani, ''Adaptive Method for Feature Selection in the Machine Learning Context,'' Engineering, Technology & Applied Science Research, vol. 14, no. 3, pp. 14295–14300, June 2024. DOI: https://doi.org/10.48084/etasr.7401
M. C. Popescu, V. E. Balas, L. Perescu-Popescu, and N. Mastorakis, ''Multilayer Perceptron and Neural Networks,'' WSEAS Transactions on Circuits and Systems, vol. 8, no. 7, pp. 579–588, July 2009.
K. O’Shea and R. Nash, ''An Introduction to Convolutional Neural Networks.'' arXiv, Dec. 02, 2015.
C. Thrampoulidis, S. Oymak, and B. Hassibi, ''Regularized Linear Regression: A Precise Analysis of the Estimation Error,'' in Proceedings of the 28th Conference on Learning Theory, June 2015, pp. 1683–1709.
V. Fonti and E. Belitser, Feature Selection using LASSO. VU Amsterdam, 2017.
G. C. McDonald, ''Ridge regression,'' WIREs Computational Statistics, vol. 1, no. 1, pp. 93–100, July 2009. DOI: https://doi.org/10.1002/wics.14
H. Zou and T. Hastie, ''Regularization and Variable Selection Via the Elastic Net,'' Journal of the Royal Statistical Society Series B: Statistical Methodology, vol. 67, no. 2, pp. 301–320, Apr. 2005. DOI: https://doi.org/10.1111/j.1467-9868.2005.00503.x
R. Quinlan, ''Statlog (Australian Credit Approval).'' UCI Machine Learning Repository, 1987.
H. Hofmann, ''Statlog (German Credit Data).'' UCI Machine Learning Repository, 1994.
C. Sano, ''Japanese Credit Screening.'' UCI Machine Learning Repository, 1992.
B. H. Baltagi, Econometric Analysis of Panel Data. John Wiley & Sons, 2005.
J. Crook, ''Credit Scoring and its Applications,'' Journal of the Operational Research Society, vol. 52, pp. 997–1006, 2002. DOI: https://doi.org/10.1057/palgrave.jors.2601178
Downloads
How to Cite
License
Copyright (c) 2025 Chinh Xuan Pham, Huynh Ngoc Trinh, Long Quoc Tran
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
