A method for increasing accuracy of credit imbalanced data
Quarterly Journal of Securities Exchange

Quarterly Journal of Securities Exchange

A method for increasing accuracy of credit imbalanced data

Document Type : Original Article

Authors
Arash GhorbanniaDelavar 1
Sadaf Sadat Ziya 2
1 Associate Professor, Department of Computer Engineering, Faculty of Engineering, Payame Noor University, Tehran, Iran.
2 M.Sc. Graduate, Department of Computer Engineering, Faculty of Engineering, Payame Noor University, Tehran, Iran.
10.22034/jse.2025.12096.2066
Abstract
The main goal of this research is to provide a method that can be used to increase the accuracy of credit imbalance data. Financial fraud is a fundamental problem that affects both the financial sector and life and plays an important role in affecting the integrity and trust in the financial sector, as well as the cost of living. Data classification in support vector machine plays a very important role in increasing accuracy. For this purpose, we will present a method for credit imbalance data classification using support vector machine and deep belief network. With a case study on the methods of deep belief network and support vector machine, unbalanced credit data has not been taken into consideration, and there has also been data redundancy and duplicate data in these methods. We want to reduce data redundancy and duplicate data and finally increase the weight of data accuracy for credit imbalanced data using feature selection and kernel modification method.
Keywords
imbalanced data
credit imbalanced data
credit classification
accuracy of imbalanced data
accuracy
Chang, Y. C; Chang, K. H; & Wu, G. J. (2018). Application of eXtreme gradient boosting trees in the construction of credit risk assessment models for financial institutions. Applied Soft Computing, 73, 914–920. https://doi.org/10.1016/j.asoc.2018.09.029
Danenas, P; & Garsva, G. (2012). Credit risk evaluation modeling using evolutionary linear SVM classifiers and sliding window approach. Procedia Computer Science, 9, 1324–1333. https://doi.org/10.1016/j.procs.2012.04.145
Das, S; Meghanath, A; Behera, B. K; Mumtaz, S; Al-Kuwari, S; & Farouk, A. (2024). QFDNN: A resource-efficient variational quantum feature deep neural networks for fraud detection and loan prediction. Expert Systems with Applications, 258, 122194. https://doi.org/10.1109/TCSS.2025.3568618
Ding, Y; Jia, M; Zhuang, J; & Ding, P. (2022). Deep imbalanced regression using cost-sensitive learning and deep feature transfer for bearing remaining useful life estimation. Applied Soft Computing, 127, 109271. https://doi.org/10.1016/j.asoc.2022.109271
GhorbanniaDelavar, A; & Ziya, S. (2025). IDCOST: A Method for Increasing Data Criterion Service by Scoring Credit Imbalanced Data Using Applied SVM. Journal of Modeling in Engineering, 23(81), 1–18. https://doi.org/10.22075/jme.2025.31252.2493. (In Persian).
GhorbanniaDelavar, A; Noori Lahrood, B; & Zekriyahpanah Gashti, M. (2011). ERPDRT: A novel real-time framework in integrated distributed system resources, secure with data mining mechanisms. 2011 IEEE 3rd International Conference on Communication Software and Networks, 61–65. https://doi.org/10.1109/iccsn.2011.6013776
GhorbanniaDelavar, A; & Jafari, Z. (2015). A method for data classification reduction using weighting technique in SVM+. Computer Science and Information Technology, 13 (1), 162351e. https://jcsit.ir/article_162351.html. (In Persian).
Giusti, C; Guarnera, L; Casu, M; & Battiato, S. (2025). Fraud is not just rarity: A causal prototype attention approach to realistic synthetic oversampling. Machine Learning with Applications, 21, 101345. https://doi.org/10.48550/arXiv.2507.14706
Gunnarsson, B. R; Vanden Broucke, S; Baesens, B; Óskarsdóttir, M; & Lemahieu, W. (2021). Deep learning for credit scoring: Do or don’t? European Journal of Operational Research, 295(1), 292–305. https://doi.org/10.1016/j.ejor.2021.03.006
Gupta, R. K; Hassan, A; Majhi, S. K; Parveen, N; Zamani, A. T; Anitha, R; Ojha, B; Singh, A. K; & Muduli, D. (2025). Enhanced framework for credit card fraud detection using robust feature selection and a stacking ensemble model approach. Results in Engineering, 26, 105084. https://doi.org/10.1016/j.rineng.2025.105084
Malek Mohammadi, M. R; Saeedi, A; & Matinfard, M. (2020). Investigating the systematic and unsystematic factors affecting credit risk in the Iranian banking system. Quarterly Journal of Securities Exchange, 13(49), 134-159. https://doi.org/10.22034/jse.2020.11061.1317. (In Persian).
Mohagheghnia, M. J; Ghorbanizadeh, V; & Khanzadeh, M. (2021). Dimensions of credit rating of Iranian banks. Quarterly Journal of Securities Exchange, 14(54), 63-84. https://doi.org/10.30495/jsed.2021.1921323.2038. (In Persian).
Sharma, R. (2025). AI-powered neural networks detecting anomalous patterns in real-time financial transactions. Intelligent Systems with Applications, 23, 200037. https://doi.org/10.52783/jisem.v10i59s.12995
Tian, Z; Xiao, J; Feng, H; & Wei, Y. (2020). Credit Risk Assessment based on Gradient Boosting Decision Tree. Procedia Computer Science, 174, 150–160. https://doi.org/10.1016/j.procs.2020.06.070 
Yu, L; Yao, X; Wang, S; & Lai, K. (2011). Credit risk evaluation using a weighted least squares SVM classifier with design of experiment for parameter selection. Expert Systems With Applications, 38(12), 15392–15399. https://doi.org/10.1016/j.eswa.2011.06.023
Yu, L; Zhou, R; Tang, L; & Chen, R. (2018). A DBN-based resampling SVM ensemble learning paradigm for credit classification with imbalanced data. Applied Soft Computing, 69, 192–202. https://doi.org/10.1016/j.asoc.2018.04.049  
Zhang, Q; Wang, J; Lu, A; Wang, S; & Ma, J. (2017). An improved SMO algorithm for financial credit risk assessment – Evidence from China’s banking. Neurocomputing, 272, 314–325. https://doi.org/10.1016/j.neucom.2017.07.002
Zhang, T; Zhang, W; Xu, W; & Hao, H. (2018). Multiple instance learning for credit risk assessment with transaction data. Knowledge-Based Systems, 161, 65–77.https://doi.org/10.1016/j.knosys.2018.07.030
Zhang, Y; Wang, G; Chung, F. L; & Wang, S. (2021). Support vector machines with the known feature-evolution priors. Knowledge-Based Systems, 223, 107048. https://doi.org/10.1016/j.knosys.2021.107048
 
Quarterly Journal of Securities Exchange
Volume 18, Issue 72
Autumn 2025
Pages 242-268