Abstract

The health of the banking sector is a key determinant of financial stability and economic resilience, making reliable assessment methods essential for regulators and stakeholders. Conventional statistical models, however, often lack interpretability and alignment with supervisory frameworks. This study introduces a transparent classification approach for bank health evaluation by integrating the CAMEL framework covering capital, asset quality, management, earnings, and liquidity with the Decision Tree C4.5 algorithm. Using secondary data from the Financial Services Authority of Indonesia, the dataset comprises 170 observations from 34 banks during 2019–2023. The research process involves data cleaning, preprocessing, label encoding, and partitioning into training and testing subsets with an 80:20 ratio. The C4.5 algorithm constructs the decision tree by iteratively selecting attributes with the highest information gain to minimize entropy, producing a model that classifies banks into four categories: healthy, fairly healthy, less healthy, and unhealthy. Results show that the composite CAMEL score offers the strongest discriminative power, serving as the root node and the most significant predictor of bank health. Model evaluation through precision, recall, and F1-score confirms consistent predictive performance while preserving interpretability. Unlike prior studies focusing mainly on credit risk or bankruptcy prediction, this research delivers a regulatory-oriented framework that is comprehensive, practical, and relevant for strengthening supervisory practices.

References

• S. A. Athari, F. Irani, and A. AlAl Hadood, “Country risk factors and banking sector stability: Do countries’ income and risk-level matter? Evidence from global study,” Heliyon, vol. 9, no. 10, 2023, Art. no. e20398. DOI: 10.1016/j.heliyon.2023.e20398.
• A. Demirgüç-Kunt, L. Klapper, D. Singer, and S. Ansar, The Global Findex Database 2021: Financial Inclusion, Digital Payments, and Resilience in the Age of COVID-19. Washington, DC, USA: World Bank, 2022. DOI: 10.1596/978-1-4648-1897-4.
• European Central Bank, Financial Stability Review. Frankfurt, Germany: European Central Bank, Nov. 2023.
• A. Citterio, “Bank failure prediction models: Review and outlook,” Socio-Economic Planning Sciences, vol. 92, 2024, Art. no. 101818. DOI: 10.1016/j.seps.2024.101818.
• E. Baffour Gyau, M. Appiah, B. A. Gyamfi, T. Achie, and M. A. Naeem, “Transforming banking: Examining the role of AI technology innovation in boosting banks financial performance,” International Review of Financial Analysis, vol. 96, 2024, Art. no. 103700. DOI: 10.1016/j.irfa.2024.103700.
• O. Abdelsalam, A. Chantziaras, N. L. Joseph, and N. Tsileponis, “Trust matters: A global perspective on the influence of trust on bank market risk,” Journal of International Financial Markets, Institutions & Money, vol. 92, 2024, Art. no. 101959. DOI: 10.1016/j.intfin.2024.101959.
• H. F. Assous, “Prediction of banks efficiency using feature selection method: Comparison between selected machine learning models,” Complexity, vol. 2022, 2022, Art. no. 3374489. DOI: 10.1155/2022/3374489.
• L. J. Vásquez-Serpa, C. Rodríguez, J. R. Pérez-Núñez, and C. Navarro, “Challenges of artificial intelligence for the prevention and identification of bankruptcy risk in financial institutions: A systematic review,” Journal of Risk and Financial Management, vol. 18, no. 1, 2025, Art. no. 26. DOI: 10.3390/jrfm18010026.
• J. P. Noriega, L. A. Rivera, and J. A. Herrera, “Machine learning for credit risk prediction: A systematic literature review,” Data, vol. 8, no. 11, 2023, Art. no. 169. DOI: 10.3390/data8110169.
• A. Citterio and F. S. Fontana, “Bank distress prediction: A machine learning approach,” Expert Systems with Applications, vol. 177, 2021, Art. no. 114960. DOI: 10.1016/j.eswa.2021.114960.
• T. M. Pham and H. T. Nguyen, “Determinants of bank stability: Evidence from emerging markets,” Research in International Business and Finance, vol. 60, 2022, Art. no. 101602. DOI: 10.1016/j.ribaf.2021.101602.
• S. Barboza, H. Kimura, and E. Altman, “Machine learning models and bankruptcy prediction,” Journal of Banking & Finance, vol. 140, 2022, Art. no. 106531. DOI: 10.1016/j.jbankfin.2022.106531.
• M. S. Khan, S. Scheule, and E. Wu, “Predicting bank failure using machine learning techniques,” International Review of Financial Analysis, vol. 74, 2021, Art. no. 101662. DOI: 10.1016/j.irfa.2021.101662.
• A. Alaka et al., “Systematic review of supervised machine learning in financial risk prediction,” Expert Systems with Applications, vol. 168, 2021, Art. no. 114280. DOI: 10.1016/j.eswa.2020.114280.
• S. García, J. Luengo, and F. Herrera, “Data preprocessing in data mining,” Knowledge-Based Systems, vol. 215, 2021, Art. no. 106740. DOI: 10.1016/j.knosys.2020.106740.
• A. K. Jain and B. B. Gupta, “Machine learning based financial risk prediction: A systematic review,” IEEE Access, vol. 9, pp. 131825–131845, 2021. DOI: 10.1109/ACCESS.2021.3114306.
• M. Zięba, S. K. Tomczak, J. M. Tomczak, and J. Świątek, “Ensemble boosted trees with synthetic features generation in financial prediction,” Expert Systems with Applications, vol. 157, 2020, Art. no. 113477. DOI: 10.1016/j.eswa.2020.113477.
• P. Biecek and T. Burzykowski, “Explanatory model analysis in machine learning for financial applications,” Information Sciences, vol. 571, pp. 158–176, 2021. DOI: 10.1016/j.ins.2021.04.043.
• L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. DOI: 10.1023/A:1010933404324.
• J. R. Quinlan, “Induction of decision trees,” Machine Learning, vol. 1, no. 1, pp. 81–106, 1986. DOI: 10.1023/A:1022643204877.
• J. R. Quinlan, C4.5: Programs for Machine Learning. San Mateo, CA, USA: Morgan Kaufmann, 1993.
• S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” in Advances in Neural Information Processing Systems, vol. 30, 2017.
• F. Petropoulos, A. Apiletti, V. Assimakopoulos, and M. Papadopoulos, “Explainable artificial intelligence in finance: A systematic review,” Expert Systems with Applications, vol. 206, 2022, Art. no. 117749. DOI: 10.1016/j.eswa.2022.117749.
• A. Bussmann, N. Giudici, D. Marinelli, and J. Papenbrock, “Explainable machine learning in credit risk management,” Computational Economics, vol. 57, no. 1, pp. 203–216, 2021. DOI: 10.1007/s10614-020-10042-0.
• M. T. Ribeiro, S. Singh, and C. Guestrin, “Why should I trust you? Explaining the predictions of any classifier,” in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 1135–1144. DOI: 10.1145/2939672.2939778.
• J. Friedman, T. Hastie, and R. Tibshirani, “Additive logistic regression: A statistical view of boosting,” Annals of Statistics, vol. 28, no. 2, pp. 337–407, 2000. DOI: 10.1214/aos/1016218223.
• G. Louppe, L. Wehenkel, A. Sutera, and P. Geurts, “Understanding variable importances in forests of randomized trees,” in Advances in Neural Information Processing Systems, vol. 26, 2013.
• H. Ishwaran and U. B. Kogalur, “Random survival forests for R,” R News, vol. 7, no. 2, pp. 25–31, 2007.
• R. B. Kearns and Y. Mansour, “On the boosting ability of top-down decision tree learning algorithms,” Journal of Computer and System Sciences, vol. 58, no. 1, pp. 109–128, 1999. DOI: 10.1006/jcss.1998.1605.
• P. Domingos, “A few useful things to know about machine learning,” Communications of the ACM, vol. 55, no. 10, pp. 78–87, 2012. DOI: 10.1145/2347736.2347755.
• T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785–794. DOI: 10.1145/2939672.2939785.