Risk Erken Uyarı Modellerinde Destek Vektör Makinesinin Genetik Algoritma ile Parametre Optimizasyonu

Öz

Makine Öğrenimi ve Derin Öğrenme algoritmaları, kredi verenler tarafından risk erken uyarı modellerinde yaygın olarak kullanılmaktadır. Makine Öğrenmesi ve Derin Öğrenme algoritmaları ile bireysel ve kurumsal müşterilerin risk seviyeleri hesap ve müşteri bazında belirlenmektedir. Kredi verenler, müşterinin veya hesabın ödeme performansını Makine Öğrenmesi ve Derin Öğrenme algoritmaları yardımıyla değerlendirerek riski yönetmek ister. Kredi verenler arasında önemli bir yere sahip olan bankalar, müşteri bilgilerini kullanarak öğrenme algoritmaları yardımıyla risk erken uyarı modelleri geliştirmektedirler. Risk erken uyarı modellerinin geliştirilmesi sürecinde bankalar bireysel segment için genellikle müşteri bilgileri ve kredi bürosu bilgilerini kullanırken, kurumsal segment için finansal, finansal olmayan ve davranış bazlı bilgileri kullanmaktadırlar. Bu çalışmada kurumsal hizmet segmentindeki müşterilere yönelik bir risk erken modelinin geliştirilmesi planlanmaktadır. Kurumsal hizmet segmentindeki müşteriler için Bilanço ve Gelir Tablosu kalemleri kullanılmıştır. Bu tablolar kullanılarak risk erken uyarı modelleri için finansal rasyolar hesaplanmıştır. Risk erken uyarı modellerinin geliştirilmesinde yeni bir özellik seçme yaklaşımı olarak Karşılıklı Bilgi yöntemi, denetimli öğrenme yaklaşımı olarak ise Destek Vektör Makinesi yöntemi (doğrusal fonksiyon, radyal temel fonksiyon ve sigmoid fonksiyon) kullanılmıştır. Komşuluk metriği (k) değiştirilerek, Karşılıklı Bilgi yöntemiyle özellik seçimi sürecinde önemli örüntüler keşfedilmiştir. Meta-sezgisel algoritmalar arasında yer alan Genetik Algoritma ile Destek Vektör Makinesi modelleri için en uygun C ve gamma parametreleri belirlenmeye çalışılmıştır. Bu veri seti için küçük komşuluk ölçüsünün modellerin öğrenme ve performansları üzerinde önemli bir etkiye sahip olduğu sonucuna varılmıştır.

Anahtar Kelimeler

• Risk Erken Uyarı Modelleri
• Karşılıklı Bilgi
• Destek Vektör Makinesi
• Parametre Optimizasyonu
• Genetik Algoritma

The Parameter Optimization of Support Vector Machine with Genetic Algorithm in Risk Early Warning Models

Öz

Machine Learning algorithms are widely used by lenders in risk early warning models. With Machine Learning, the risk levels of individual and corporate customers are determined at the account and customer level. Lenders want to manage risk by evaluating the payment performance of customer or account with the help of Machine Learning algorithms. Banks, which have an important place among lenders, develop risk early warning models with the help of learning algorithms using customer information. In the development process of risk early warning models, while banks generally use customer information and credit bureau information for the individual segment, they use financial, non-financial and behaviour-based information for the corporate segment. In this study, it is planned to develop a risk early model for customers in corporate service segment. For the customers of corporate service segment, Balance Sheet and Income Statement items were used and the financial ratios were calculated for risk early warning models. In the development of risk early warning models, Mutual Information method was used as a novel feature selection approach and Support Vector Machine method (linear function, radial basis function and sigmoid function) was used as a supervised learning approach. By changing the neighbourhood metric (k), important patterns were discovered with the Mutual Information method in feature selection process. The optimal C and gamma parameters for Support Vector Machine models have been tried to be determined with the Genetic Algorithm, which is among the Meta-Heuristic algorithms. In order to find the optimal metrics in this study, the metric values for all parameters of the SVM model (function specific) have been kept quite wide. In this dataset of corporate service customers, the small neighbourhood metric has been found to have a significant impact on model learning and performance.

Anahtar Kelimeler

• Risk Early Warning Models
• Mutual Information
• Support Vector Machine
• Parameter Optimization
• Genetic Algorithm

Kaynakça

1. Farooq, U., Jibran Qamar, M. A., & Haque, A. (2018). A three-stage dynamic model of financial distress. Managerial Finance, 44(9), 1101–1116. https://doi.org/10.1108/MF-07-2017-0244
2. Kumbure, M. M., Lohrmann, C., Luukka, P., & Porras, J. (2022). Machine learning techniques and data for stock market forecasting: A literature review. Expert Systems with Applications, 197, 116659. https://doi.org/10.1016/j.eswa.2022.116659
3. Geršl, A., & Jašová, M. (2018). Credit-based early warning indicators of banking crises in emerging markets. Economic Systems, 42(1), 18–31. https://doi.org/10.1016/j.ecosys.2017.05.004
4. Shen, C., Lee, Y., & Fang, H. (2020). Predicting banking crises based on credit, housing and capital booms. International Finance, 23(3), 472–505. https://doi.org/10.1111/infi.12367
5. Zhang, C., Wang, Z., & Lv, J. (2022). Research on early warning of agricultural credit and guarantee risk based on deep learning. Neural Computing and Applications, 34(9), 6673–6682. https://doi.org/10.1007/s00521-021-06114-3
6. Feng, Q., Chen, H., & Jiang, R. (2021). Analysis of early warning of corporate financial risk via deep learning artificial neural network. Microprocessors and Microsystems, 87, 104387. https://doi.org/10.1016/j.micpro.2021.104387
7. Kou, G., Xu, Y., Peng, Y., Shen, F., Chen, Y., Chang, K., & Kou, S. (2021). Bankruptcy prediction for SMEs using transactional data and two-stage multiobjective feature selection. Decision Support Systems, 140, 113429. https://doi.org/10.1016/j.dss.2020.113429
8. Du, G., Liu, Z., & Lu, H. (2021). Application of innovative risk early warning mode under big data technology in Internet credit financial risk assessment. Journal of Computational and Applied Mathematics, 386, 113260. https://doi.org/10.1016/j.cam.2020.113260

9. Wen, C., Yang, J., Gan, L., & Pan, Y. (2021). Big data driven Internet of Things for credit evaluation and early warning in finance. Future Generation Computer Systems, 124, 295–307. https://doi.org/10.1016/j.future.2021.06.003
10. Rosa, N. L. (2020). Analysing Financial Performance: Using Integrated Ratio Analysis (1st ed.).Routledge. https://doi.org/10.4324/9781003092575
11. Ravisankar, P., Ravi, V., Raghava Rao, G., & Bose, I. (2011). Detection of Financial Statement Fraud and Feature Selection using Data Mining Techniques. Decision Support Systems, 50(2), 491–500. https://doi.org/10.1016/j.dss.2010.11.006
12. Zhang, J. (2020). Investment risk model based on intelligent fuzzy neural network and VaR. Journal of Computational and Applied Mathematics, 371, 112707. https://doi.org/10.1016/j.cam.2019.112707
13. Lin, M. (2022). Innovative Risk Early Warning Model under Data Mining Approach in Risk Assessment of Internet Credit Finance. Computational Economics, 59(4), 1443–1464. https://doi.org/10.1007/s10614-021-10180-z
14. Lahmiri, S., Bekiros, S., Giakoumelou, A., & Bezzina, F. (2020). Performance assessment of ensemble learning systems in financial data classification. Intelligent Systems in Accounting, Finance and Management, 27(1), 3–9. https://doi.org/10.1002/isaf.1460
15. Bhatore, S., Mohan, L., & Reddy, Y. R. (2020). Machine Learning Techniques for Credit Risk Evaluation: A Systematic Literature Review. Journal of Banking and Financial Technology, 4(1), 111–138. https://doi.org/10.1007/s42786-020-00020-3
16. Zhang, W., He, H., & Zhang, S. (2019). A Novel Multi-Stage Hybrid Model with Enhanced Multi-Population Niche Genetic Algorithm: An Application in Credit Scoring. Expert Systems with Applications, 121, 221–232. https://doi.org/10.1016/j.eswa.2018.12.020
17. Catullo, E., Gallegati, M., & Palestrini, A. (2015). Towards a credit network based early warning indicator for crises. Journal of Economic Dynamics and Control, 50, 78–97. https://doi.org/10.1016/j.jedc.2014.08.011
18. Luo, C., Wu, D., & Wu, D. (2017). A deep learning approach for credit scoring using credit default swaps. Engineering Applications of Artificial Intelligence, 65, 465–470. https://doi.org/10.1016/j.engappai.2016.12.002
19. Hilal, W., Gadsden, S. A., & Yawney, J. (2022). Financial Fraud: A Review of Anomaly Detection Techniques and Recent Advances. Expert Systems with Applications, 193, 116429. https://doi.org/10.1016/j.eswa.2021.116429
20. Bequé, A., & Lessmann, S. (2017). Extreme Learning Machines for Credit Scoring: An Empirical Evaluation. Expert Systems with Applications, 86, 42–53. https://doi.org/10.1016/j.eswa.2017.05.050
21. Koutanaei, F. N., Sajedi, H., & Khanbabaei, M. (2015). A hybrid data mining model of feature selection algorithms and ensemble learning classifiers for credit scoring. Journal of Retailing and Consumer Services, 27, 11–23. https://doi.org/10.1016/j.jretconser.2015.07.003
22. Nguyen, M. H., & de la Torre, F. (2010). Optimal feature selection for support vector machines. Pattern Recognition, 43(3), 584–591. https://doi.org/10.1016/j.patcog.2009.09.003
23. Jadhav, S., He, H., & Jenkins, K. (2018). Information Gain Directed Genetic Algorithm Wrapper Feature Selection for Credit Rating. Applied Soft Computing, 69, 541–553. https://doi.org/10.1016/j.asoc.2018.04.033
24. Vijayanand, R., Devaraj, D., & Kannapiran, B. (2018). Intrusion Detection System for Wireless Mesh Network using Multiple Support Vector Machine Classifiers with Genetic-Algorithm-Based Feature Selection. Computers & Security, 77,304–314. https://doi.org/10.1016/j.cose.2018.04.010
25. Talbi, E.-G. (2009). Metaheuristics: From Design To Implementation. John Wiley & Sons.
26. Manurung, J., Mawengkang, H., & Zamzami, E. (2017). Optimizing Support Vector Machine Parameters with Genetic Algorithm for Credit Risk Assessment. Journal of Physics: Conference Series, 930, 012026. https://doi.org/10.1088/1742-6596/930/1/012026
27. İlhan, İ., & Tezel, G. (2013). A genetic algorithm–support vector machine method with parameter optimization for selecting the tag SNPs. Journal of Biomedical Informatics, 46(2), 328–340. https://doi.org/10.1016/j.jbi.2012.12.002
28. Onay, C., & Öztürk, E. (2018). A review of credit scoring research in the age of Big Data. Journal of Financial Regulation and Compliance, 26(3), 382–405. https://doi.org/10.1108/JFRC-06-2017-0054
29. Işık, M. (2023). Dataset. Işık, Muhammed (2023), “Early Warning Model Dataset for Corporate Segment”, Mendeley Data, V5, doi: 10.17632/pp599dy9c8.5
30. Bishop, C.M., 2006. Pattern recognition and machine learning, Information science and statistics. Springer, New York
31. Su, X., Li, L., Shi, F., & Qian, H. (2018). Research on the Fusion of Dependent Evidence Based on Mutual Information. IEEE Access, 6, 71839–71845. https://doi.org/10.1109/Access.2018.2882545
32. Barraza, N., Moro, S., Ferreyra, M., & de la Peña, A. (2019). Mutual Information and Sensitivity Analysis for Feature Selection in Customer Targeting: A Comparative Study. Journal of Information Science, 45(1), 53–67. https://doi.org/10.1177/0165551518770967
33. Yan, C., Kang, X., Li, M., & Wang, J. (2021). A Novel Feature Selection Method on Mutual Information and Improved Gravitational Search Algorithm for High Dimensional Biomedical Data. 2021 13th International Conference on Computer and Automation Engineering (ICCAE), 24–30. https://doi.org/10.1109/ICCAE51876.2021.9426130