Enhancing Credit Risk Assessment in Germany: A GAN-Based Approach with Forward-Looking Variables
Article Sidebar
Main Article Content
Abstract
Background and Aim: Credit consumption has become a cornerstone of modern economies, making accurate credit evaluation essential to minimizing loan default risks. However, existing credit scoring systems face several challenges, including data imbalance, inefficient sample ratios, and the need for more precise indicator weighting. This study aims to enhance credit scoring for German credit card users by addressing these issues and integrating forward-looking variables to improve prediction accuracy and model stability.
Materials and Methods: This research utilizes the UCI Statlog (German Credit Data) dataset, employing a preprocessing pipeline that includes normalization, encoding, and data augmentation via Generative Adversarial Networks (GANs) to address data imbalance. The GAN-based model applies SoftMax classification to predict defaults while utilizing principal component analysis (PCA) combined with macroeconomic and industry-specific variables to enhance the adaptability of the model.
Results: Compared with traditional oversampling methods, GAN can generate samples that are closer to the true data distribution, thereby avoiding overfitting and data distortion. The GAN-based model significantly improved predictive accuracy, increasing overall accuracy from 74.25% to 87.92% following data augmentation. The integration of forward-looking variables further enhanced model performance, demonstrating the potential of GANs and dynamic economic factors in credit scoring.
Conclusion: This study proposes an advanced credit scoring system that, compared to existing models in the German market, effectively alleviates data imbalance and improves prediction accuracy by enhancing and introducing future variables based on GAN. The findings suggest that GANs can serve as a powerful tool in credit risk assessment, particularly in cases where labeled data is limited. Future research should explore the scalability of this approach across various financial risk prediction tasks.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright on any article in the International Journal of Sociologies and Anthropologies Science Reviews is retained by the author(s) under the under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. Permission to use text, content, images, etc. of publication. Any user to read, download, copy, distribute, print, search, or link to the full texts of articles, crawl them for indexing, pass them as data to software, or use them for any other lawful purpose. But do not use it for commercial use or with the intent to benefit any business.
References
Ballouk, H., Ben Jabeur, S., Challita, S., & Chen, C. (2024). Financial stability: A scientometric analysis and research agenda. Research in International Business and Finance, 70, 102294.
Bansal, M., Goyal, A., & Choudhary, A. (2022). A comparative analysis of K-nearest neighbor, genetic, support vector machine, decision tree, and long short-term memory algorithms in machine learning. Decision Analytics Journal, 3, 100071.
Bhatore, S., Mohan, L., & Reddy, R. (2020). Machine learning techniques for credit risk evaluation: Systematic literature review. Journal of Banking and Financial Technology, 4(1), 111–138.
Chen, Y., Kumara, E., & Sivakumar, V. (2021). Investigation of the finance industry on risk awareness model and digital economic growth. Annals of Operations Research, 326(6), 1–22.
Choudhry, M. (2022). The principles of banking (2nd ed.). Wiley.
Fromhold-Eisebith, M., Marschall, P., Peters, R., & Thomes, P. (2021). Torn between digitized future and context-dependent past–How implementing ‘Industry 4.0’ production technologies could transform the German textile industry. Technological Forecasting and Social Change, 166, 120620.
Frydman, R., & Goldberg, M. D. (2023). Imperfect knowledge economics: Exchange rates and risk. Springer Nature.
Gorbachev, O., & Luengo-Prado, M. J. (2019). The credit card debt puzzle: The role of preferences, credit access risk, and financial literacy. The Review of Economics and Statistics, 101(2), 294–309.
Grodzicki, D. (2023). The evolution of competition in the credit card market. SSRN. https://doi.org/10.2139/ssrn.4493211
He, Z., & Wei, W. (2023). China's financial system and economy: A review. Annual Review of Economics, 15(1), 451–483.
Irshad, S. M. (2024). Theorizing risk economics. In Economics of Disasters and Climate Change: Risk and Uncertainties (pp. 1–37). Springer Nature Singapore.
Jiang, H., Zhang, X., & Lee, C. (2020). Credit risk evaluation using supervised and unsupervised learning models. Journal of Risk Finance, 21(2), 111–125.
Naili, M., & Lahrichi, Y. (2022). The determinants of banks' credit risk: Review of the literature and future research agenda. International Journal of Finance & Economics, 27(1), 334–360.
Roll, S., Grinstein-Weiss, M., Steensma, J., & Deruyter, A. (2020). Developing financial assets for lower-income households. In Toward a Livable Life: A 21st Century Agenda for Social Work (Ch. 6). Oxford University Press.
Sang, B. (2021). Application of genetic algorithm and BP neural network in supply chain finance under information sharing. Journal of Computational and Applied Mathematics, 384, 113170.
Wang, X., Yu, K., Wu, S., Gu, J., Liu, Y., Dong, C., Qiao, Y., & Loy, C. C. (2019). ESRGAN: Enhanced super-resolution generative adversarial networks. In Computer Vision – ECCV 2018 Workshops (pp. 63–79). Springer International Publishing.
Wu, Z., Hu, L., Lin, Z., & Tan, Y. (2021). Competition and distortion: A theory of information bias on the peer-to-peer lending market. Information Systems Research, 32(4), 1140–1154.
Zheng, Z., He, J., Yang, Y., Zhang, M., Wu, D., Bian, Y., & Cao, J. (2023). Does financial leverage volatility induce systemic financial risk? Empirical insight based on the Chinese fintech sector. Managerial and Decision Economics, 44(2), 1142–1161.
