SavedAdd your journal

Journals / İstanbul Ticaret Üniversitesi Teknoloji ve Uygulamalı Bilimler Dergisi / 2026 / Cilt: 9 Sayı: 1

PREDICTING THE CALL RISK OF LETTERS OF GUARANTEE IN THE BANKING SECTOR USING XGBOOST

Bankacılık Sektöründe Teminat Mektubu Tazmin Riskinin XGBoost Algoritması ile Öngörülmesi

Fatih Yıldız(ISTANBUL COMMERCE UNIVERSITY, INSTITUTE OF SCIENCE, INDUSTRIAL ENGINEERING (MASTER) (WITHOUT THESIS))0000-0002-5652-3762
Berk Ayvaz(İstanbul Ticaret Üniversitesi)0000-0002-8098-3611
Pages
63–89
Publication Date
2026-08-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Model performance was evaluated through the ROC(Receiver Operating Characteristic) curve and AUC(Area Under the Curve) metric, and the results indicate that the XGBoost model achieves a high discriminative capability with an AUC value of 0,88.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:This study aims to predict the call risk of letters of guarantee in the banking sector using a machine learning-based approach.
📊
Key Findings & Data:Model performance was evaluated through the ROC(Receiver Operating Characteristic) curve and AUC(Area Under the Curve) metric, and the results indicate that the XGBoost model achieves a high discriminative capability with an AUC value of 0,88.
💡
Conclusion & Impact:By showing that the XGBoost algorithm can be utilized as an objective decision support mechanism and an early warning system for banks, this study provides an original contribution to the relatively limited literature on letter of guarantee risk management.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:bankacılık · XGBoost · makine öğrenmesi

Abstract

This study aims to predict the call risk of letters of guarantee in the banking sector using a machine learning-based approach. In this study, the XGBoost classification algorithm was applied using financial ratios obtained from artificial data, based on lower and upper threshold values of the independent variables. Model performance was evaluated through the ROC(Receiver Operating Characteristic) curve and AUC(Area Under the Curve) metric, and the results indicate that the XGBoost model achieves a high discriminative capability with an AUC value of 0,88. The findings demonstrate that the call risk of letters of guarantee can be predicted with low classification error. According to the feature importance analysis, EBITDA(Earnings Before Interest, Taxes, Depreciation and Amortization) / Net Sales, Debt / Total Assets, and Cash Requirement were identified as the most influential variables in risk prediction. By showing that the XGBoost algorithm can be utilized as an objective decision support mechanism and an early warning system for banks, this study provides an original contribution to the relatively limited literature on letter of guarantee risk management.

Özet

Bu çalışma bankacılık sektöründe teminat mektubu tazmin riskinin makine öğrenmesi tabanlı bir yaklaşımla öngörülmesini amaçlamaktadır. Çalışma kapsamında bağımsız değişkenlerin alt ve üst eşik değerlerine bağlı kalınarak yapay veriler üzerinden elde edilen finansal oranlar kullanılarak XGBoost sınıflandırma algoritması uygulanmıştır. Model performansı ROC(alıcı işletim karakteristiği) eğrisi ve AUC (eğri altında kalan alan) metriği üzerinden değerlendirilmiş; elde edilen bulgular, XGBoost modelinin 0,88 AUC değeri ile yüksek bir ayırt edicilik kapasitesine sahip olduğunu göstermiştir. Sonuçlar, teminat mektuplarının nakde dönüşme riskinin düşük hata payı ile tahmin edilebildiğini ortaya koymaktadır. Değişken önem analizi bulgularına göre, FAVÖK(faaliyet ve vergi öncesi kar) / Net Satışlar, Borç / Aktif Oranı ve Nakit İhtiyacı göstergeleri risk tahmininde en kritik değişkenler olarak öne çıkmaktadır. Çalışma XGBoost algoritmasının bankalar için nesnel bir karar destek mekanizması ve erken uyarı sistemi olarak kullanılabileceğini göstererek, teminat mektubu risk yönetimi literatürüne özgün bir katkı sunmaktadır.

🔖

Cite This Article

Yıldız, F., Ayvaz, B. (2026). PREDICTING THE CALL RISK OF LETTERS OF GUARANTEE IN THE BANKING SECTOR USING XGBOOST. İstanbul Ticaret Üniversitesi Teknoloji ve Uygulamalı Bilimler Dergisi, Cilt: 9 Sayı: 1, 63–89. https://doi.org/10.56809/icujtas.1970288

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (24)

  1. Altman, E. I., & Sabato, G. (2005). Modeling credit risk for SMEs: Evidence from the U.S. market. SSRN Electronic Journal, http://dx.doi.org/10.2139/ssrn.872336
  2. Berger, A. N., & Bouwman, C. H. S. (2013). How does capital affect bank performance during financial crises? Journal of Financial Economics, 109(1), 146-176. https://doi.org/10.1016/j.jfineco.2013.02.008
  3. Berger, A. N., & Udell, G. F. (2002). Small business credit availability and relationship lending: The importance of bank organisational structure. The Economic Journal, 112(467), 32–53. https://doi.org/10.1111/1468-0297.00682
  4. Betz, F., Oprică, S., Peltonen, T. A., & Sarlin, P. (2014). Predicting distress in European banks. Journal of Banking & Finance, 45, 225-241. https://doi.org/10.1016/j.jbankfin.2013.11. 041
  5. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/ 10.1023/A:1010933404324
  6. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). https://doi.org/10.1145/2939672.2939785
  7. Chiaramonte, L., Croci, E., & Poli, F. (2015). Should we trust the Z-score? Evidence from the European banking industry. Global Finance Journal, 28, 111-131. https://doi.org/10.1016/j.gfj.2015.02.002
  8. Demir, M., ve Eken, M. H. (2015). 2008 küresel krizinin Türk bankacılık sektörüne etkileri ve anket çalışması ile analizi. Maliye ve Finans Yazıları, 1(104), 53-81. https://izlik.org/ JA99JK33AY
  9. Engin, U., ve Durer, S. (2023). Financial distress prediction from time series data using XGBoost: BIST100 of Borsa Istanbul. Doğuş Üniversitesi Dergisi 24(2), 589–604. https://doi.org/10.31671/doujournal.1238432,
  10. Fawcett, T. (2006). An introduction to ROC analysis. Pattern Recognition Letters, 27(8), 861–874. https://doi.org/10.1016/j.patrec.2005.10.010
  11. Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29(5), 1189–1232. https://doi.org/10.1214/aos/1013203451
  12. Gogas, P., Papadimitriou, T., & Agrapetidou, A. (2018). Forecasting bank failures and stress testing: A machine learning approach. International Journal of Forecasting, 34(3), 440–455. https://doi.org/10.1016/j.ijforecast.2018.01.009
  13. Hastie, T., Tibshirani, R., Friedman, J. (2009). The elements of statistical learning: Data mining, inference, and prediction (2nd ed.). Springer. https://doi.org/10.1007/978-0-387-84858-7
  14. Hosmer, D. W., Lemeshow, S., & Sturdivant, R. X. (2013). Applied logistic regression (3rd ed.). Wiley. https://doi.org/10.1002/9781118548387
  15. Hou, G., Tong, D. L., Liew, S. Y., & Choo, P. Y. (2025). Comparative analysis of resampling techniques for class imbalance in financial distress prediction using XGBoost. Mathematics, 13(13),2186. https://doi.org/10.3390/math13132186
  16. Kaufman, S., Rosset, S., Perlich, C., & Stitelman, O. (2012). Leakage in data mining: Formulation, detection, and avoidance. ACM Transactions on Knowledge Discovery from Data. 6(4), 1–21. https://doi.org/10.1145/2382577.2382579
  17. Kılcı, E. N. (2017). Bankacılık sektörü bilançolarındaki kırılganlıklar ile krizler arasındaki ilişkinin değerlendirilmesi; Türkiye örneği, 2000-01 krizleri. Finans Politik & Ekonomik Yorumlar, 54(631), 1-18. https://izlik.org/JA79SF78DT
  18. Kuhn, M., & Johnson, K. (2019). Feature engineering and selection: A practical approach for predictive models. Chapman & Hall/CRC. https://doi.org/10.1201/9781315 108230
  19. Liu, W., Fan, H., Xia, M., & Pang, C. (2022). Predicting and interpreting financial distress using a weighted boosted tree-based tree. Engineering Applications of Artificial Intelligence, 116, 105466. https://doi.org/10.1016/j.engappai.2022.105466
  20. Petropoulos, A., Siakoulis, V., Stavroulakis, E., & Vlachogiannakis, N. E. (2020). Predicting bank insolvencies using machine learning techniques. International Journal of Forecasting, 36(3), 1092–1113. https://doi.org/10.1016/j.ijforecast.2019.11.005
  21. Sayıl, G. B., ve Emir, M. (2017). Küresel finansal krizin Türk bankacılık sektörü üzerine etkileri. Uluslararası İktisadi ve İdari İncelemeler Dergisi, (19), 111-132. https://doi.org/ 10.18092/ulikidince.310747
  22. Song, Y., Jiang, M., Li, S., & Zhao, S. (2023). Class-imbalanced financial distress prediction with machine learning: Incorporating financial, management, textual, and social responsibility features into index system. Journal of Forecasting, 43(3), 593–614. https://doi.org/10.1002/for.3050
  23. Wang, K., Li, M., Cheng, J., Zhou, X., & Li, G. (2022). Research on personal credit risk evaluation based on XGBoost. Procedia Computer Science, 199, 1128–1135. https://doi.org/ 10.1016/j.procs.2022.01.143
  24. Wang, W., & Liang, Z. (2024). Financial distress early warning for Chinese enterprises from a systemic risk perspective: Based on the adaptive weighted XGBoost-bagging model. Systems, 12(2), 65. https://doi.org/10.3390/systems12020065