New researches in Islamic humanities studies

New researches in Islamic humanities studies

The Role of Deep Learning in Predicting and reducing Credit Risk: A Comparative Study of Different Algorithms on Banking Datasets

Document Type : Original Article

Authors
Gholamreza Askarzadeh 1
Isa Taheri 2
1 Financial Management, Yazd Branch, Islamic Azad University, Yazd, Iran
2 PhD student, Financial Management, Yazd Branch, Islamic Azad University, Yazd, Iran
10.22034/api.2025.2045815.1095
Abstract
Objective: The primary objective of this study is to evaluate the performance of various deep learning algorithms, including DNN, CNN, and RNN, in accurately analyzing and predicting credit risk, as well as identifying complex patterns within banking data.
Method: This study utilizes a banking dataset comprising information on loans and customer accounts. The data were fully preprocessed, and subsequently, deep learning models including DNNs, CNNs, and RNNs were trained to predict credit risk. Training and optimization techniques such as optimization algorithms and regularization methods were applied to each model. The performance of the models was assessed using key metrics such as accuracy, sensitivity, specificity, and the F1 score.
Results: The results indicate that: 
 The RNN model achieved the best performance, with an accuracy of 88% and an F1 score of 88%, effectively capturing temporal patterns and periodic variations in the banking data. 
- The DNN model obtained an accuracy of 85% and an F1 score of 84%, demonstrating strong capability in identifying complex patterns, although it was less effective in handling sequential data. 
- The CNN model reached an accuracy of 82% and an F1 score of 81%, performing well in extracting local features, but its results were inferior to those of the DNN and RNN models.
Conclusions: The study demonstrates that RNNs, due to their superior ability to analyze temporal patterns, are the most effective model for predicting and mitigating credit risk in banking data. Although DNNs and CNNs also exhibit acceptable performance, they show certain limitations compared to RNNs in specific contexts. Therefore, selecting an appropriate model should be based on the characteristics of the data and the prediction requirements, in order to enhance credit risk management processes.
Keywords
Deep Learning
Credit Risk Prediction
Credit Risk Mitigation
Machine Learning Algorithms
Subjects
خلوصی،‌ ع و خدابخشی،‌ ا. (١٤٠١). نحوه پاسخ‌ ریسک‌ اعتباری‌ بانک‌ ها به‌ شوک های‌ ارزی‌، تورمی‌ و مخارج دولت‌ در ایران، فصلنامه‌ اقتصاد مالی‌، ۱۸(۶۷).
دهقان منشادی،‌ س, م و روستا، س. (1403). تاثیر ریسک‌ اعتباری‌ و ریسک‌ نقدینگی‌ بر ثبات مالی‌ بانک‌ های‌ پذیرفته‌ شده،  دهمین‌ کنفرانس‌ بین‌ المللی‌ علوم مدیریت‌ و حسابداری‌. تهران.
ربیعی،‌ م. و. و فخاریان زاده، ی.‌ (١٤٠٣). پیش‌ بینی‌ ریسک‌ اعتباری‌ مشتریان بانکی‌ با استفاده از شبکه‌ عصبی‌ و الگوریتم‌ بهینه‌ سازی‌ بازی‌ آشوب, بیست‌ و دومین‌ کنفرانس‌ ملی‌ مهندسی‌ برق،کامپیوتر و مکانیک‌. شیروان,.
شکراللهی‌ ف و. عبدالباقی‌ عطاآبادی‌. (1403). فراتحلیل‌ عوامل‌ تعیین‌ کننده ریسک‌ اعتباری‌ بانک‌ ها,” اولین‌ همایش‌ علوم انسانی‌ با رویکرد نوین‌. آستارا.
قلی‌ زاده، ع و شالیاری،‌ ف. (1396). بررسی‌ اثرگذاری‌ متغیرهای‌ اقتصادی‌ بر ریسک‌ اعتباری‌ سیستم‌ بانکی‌ کشور, مجله‌ اقتصاد و بانکداری‌ اسلامی‌، ۱۶(۲۰).
Bodaghi, F., Owhadi, A., Khalili  Nasr, A. & Khadem Sameni, M. ( 2023). Stock  Price Forecasting  in  Iran  Stock  Market: A Comparative Analysis of Deep-learning.
Cagliero, L., Fior, J. & Garza, P., (2023). Shortlisting machine learning -based stock trading recommendations using candlestick pattern recognition, Expert Syst. Appl., 216, 119493
Dakalbab, F., Talib, M. A., Nassir, Q. & Ishak, T. (2024). Artificial intelligence in techniques in financial trading: A systematic literature review, J. King Saud Univ. Inf. Sci., 102015
Gholizade, A. & Shalyari, F. (2018). Investigating the impact of macro economics on credit risk in banking system, Economic and Islamic Journal, 6(20)
Gong, Z. (2023). Deep learning for trading and hedging in financial markets. University of Essex.
Htun, H. H., Biehl, M. & Petkov, N. ( 2023). Survey of feature selection and extraction techniques for stock market prediction, Financ. Innov, 9(1), 26.
Kaur, K., Kumar, Y. & Kaur, S. ( 2023). Artificial Intelligence and Machine Learning in Financial Services to Improve the Business System, in Computational Intelligence for Modern Business Systems: Emerging Applications and Strategies, Springer, pp3-30
Kholousi, A., & khodabahshi, A. (2021). Credit risk in banks and currency, Inflation shocks in Iran, Financial Economic Journal, 18(67).
Kulshrestha, N.,  Kamra, V.  &  Aggarwal, S. (2023). Leveraging  technical  analysis  and artificial  intelligence-optimisation  of  global  portfolio  management  through  world. learning in finance: status, development and future directions, Kybernetes,.
Lim, B. & Zohren, S. (2021). Time-series forecasting with deep learning: a survey,” Philos fusion-guided intervention, Int. J. Comput. Assist. Radiol. Surg., vol. 15, pp. 963-972.
Milke, V.  ( 2023). “Intraday  machine  learning  for  the  securities  market.”  Anglia Ruskin Research Online (ARRO
Mondal, B. & Dandapat, A. (2023). Machine learning and deep learning based stock         marketprediction considering Covid-19 as a feature, in 2022 OPJU International Technology Conference on Emerging Technologies for Sustainable Development (OTCON), IEEE, , pp. 1-6.
Rabie Fakharianzade, E. (2024). Predicting the credit risk in banks customers using  neural network.national conference in computer engineering .Shirvan
Shafiekhani, S. Namdar, P. & Rafiei, S. (2022). A COVID-19 forecasting system for hospital needs using ANFIS and LSTM models: A graphical user interface unit, Digit. Heal., 8.
Shokrollahi, F. & Abdolbaghi, A. (2024). Metaanalysis in factors affected credit risk in banks.first conference in management. Astara.
Sokolovsky, A.,  Arnaboldi, L.,  Bacardit, J. & T. Gross, T. (2023). Interpretable trading pattern designed for machine learning applications, Mach. Learn. with Appl., 11, 100448.
Verma, S., S. Sahu, P. & T Sahu, P. (2023) Stock Market Forecasting with Different Input Indicators using Machine Learning and Deep Learning Techniques: A Review., Eng Lett., 31, 1.
New researches in Islamic humanities studies
Volume 4, Issue 8 - Serial Number 8
December 2025
Pages 1-25