Macroeconomic Scalar Adjustment for Probability of Default in Expected Credit Loss Models
DOI:
https://doi.org/10.59976/jebin.v3i3.324Abstract
The expected credit loss framework established under International Financial Reporting Standards Foundation 9 is structured around three core components: probability of default, loss given default and exposure at default. Among these three elements, the probability of default component most frequently lacks a coherent mechanism for embedding macroeconomic dynamics into the estimation process, a deficiency that carries particular weight in Latin American developing economies where economic volatility is a persistent structural feature. This article applies a novel five-step macroeconomic scalar methodology for dynamically adjusting the probability of default through the systematic integration of forward-looking macroeconomic information, with empirical application to unsecured retail portfolios in Brazil and Mexico. Unsecured retail lending portfolio datasets sourced from regional banking institutions in Brazil and Mexico provide the empirical basis through which the proposed methodology is validated across two economically distinct Latin American environments. The methodology advances through five sequential stages: research and planning; data preparation; model development; scalar calculation; and model validation. Comparative modelling draws on multiple regression, generalised linear models with logit and probit specifications, and machine learning techniques encompassing feedforward neural networks, random forests and gradient boosting. Model performance is evaluated through mean absolute error, mean absolute percentage error and mean squared error. Data collection extends to December 2024. The macroeconomic scalar produced consistent and economically coherent probability of default adjustments within the expected credit loss model for both Brazil and Mexico. Each modelling technique contributed distinct analytical insights, and the scalar demonstrated reliable capacity to improve expected credit loss forecasts across environments characterised by interest rate volatility, persistent inflation and exchange rate depreciation. Embedding a macroeconomic scalar within the expected credit loss framework constitutes a disciplined and auditable method for incorporating forward-looking information while preserving the model interpretability that bank boards, auditors and regulators require in Latin American credit markets. This article delivers a replicable approach for macroeconomic probability of default adjustment in expected credit loss models calibrated specifically to Latin American economic conditions. Structured implementation guidelines are provided for practitioners operating under International Financial Reporting Standards Foundation 9 in Brazil and Mexico.
References
Alonso Robisco, A., & Carbó Martínez, J. M. (2022). Measuring the model risk-adjusted performance of machine learning algorithms in credit default prediction. Financial Innovation, 8, 70. https://doi.org/10.1186/s40854-022-00366-1
Ariza-Garzon, M. J., Arroyo, J., Caparrini, A., & Segovia-Vargas, M. J. (2020). Explainability of a Machine Learning Granting Scoring Model in Peer-to-Peer Lending. IEEE Access, 8, 64873–64890. https://doi.org/10.1109/ACCESS.2020.2984412
Breed, D. G., Verster, T., Raubenheimer, H., & Geldenhuys, G. (2021). Development of an Impairment Point in Time Probability of Default Model for Revolving Retail Credit Products: South African Case Study. Risks, 9(11), 208. https://doi.org/10.3390/risks9110208
Bussmann, N., Giudici, P., Marinelli, D., & Papenbrock, J. (2021). Explainable Machine Learning in Credit Risk Management. Computational Economics, 57, 203–216. https://doi.org/10.1007/s10614-020-10042-0
Chang, V., Baudier, P., Zhang, H., Xu, Q., Zhang, J., & Arami, M. (2024). Credit Risk Prediction Using Machine Learning and Deep Learning: A Study on the German Credit Dataset. Risks, 12(11), 174. https://doi.org/10.3390/risks12110174
Chen, Y., Yang, C., & Zhang, C. (2022). Study on the influence of IFRS 9 on the impairment of commercial bank credit card. Applied Economics Letters, 29(1), 35–40. https://doi.org/10.1080/13504851.2020.1855298
Costa e Silva, E., Lopes, I. C., Correia, A., & Faria, S. (2020). A logistic regression model for consumer default risk. Journal of Applied Statistics, 47(13–15), 2879–2894. https://doi.org/10.1080/02664763.2020.1759030
Dastile, X., Celik, T., & Potsane, M. (2020). Statistical and machine learning models in credit scoring: A systematic literature survey. Applied Soft Computing, 91, 106263. https://doi.org/10.1016/j.asoc.2020.106263
Du, N., Allini, A., & Maffei, M. (2023). How do bank managers forecast the future in the shadow of the past? An examination of expected credit losses under IFRS 9. Accounting and Business Research, 53(6), 699–722. https://doi.org/10.1080/00014788.2022.2063104
Engelmann, B. (2021). Calculating lifetime expected loss for IFRS 9: which formula is measuring what? The Journal of Risk Finance, 22(3/4), 193–208. https://doi.org/10.1108/JRF-05-2020-0113
Engelmann, B., & Nguyen, L. T. T. (2023). Global assessment of the COVID-19 impact on IFRS 9 loan loss provisions. Asian Review of Accounting, 31(1), 26–41. https://doi.org/10.1108/ARA-04-2022-0105
Fatouh, M., Bock, R., & Ouenniche, J. (2023). Impact of IFRS 9 on the cost of funding of banks in Europe. Journal of Banking Regulation, 24(2), 115–145. https://doi.org/10.1057/s41261-021-00177-x
Ghosh, S. (2024). IFRS-9, expected loan loss provisioning and bank liquidity creation: Early evidence. Accounting Research Journal, 37(4), 436–452. https://doi.org/10.1108/ARJ-03-2024-0086
Gómez-Ortega, A., Gelashvili, V., Delgado Jalón, M. L., & Rivero Menéndez, J. Á. (2022). Impact of the application of IFRS 9 on listed Spanish credit institutions: Implications from the regulatory, supervisory and auditing point of view. The Journal of Risk Finance, 23(4), 437–455. https://doi.org/10.1108/JRF-01-2022-0023
Groff, M. Z., & Mörec, B. (2021). IFRS 9 transition effect on equity in a post bank recovery environment: The case of Slovenia. Economic Research-Ekonomska Istraživanja, 34(1), 670–686. https://doi.org/10.1080/1331677X.2020.1804425
Gubareva, M. (2021). How to estimate expected credit losses – ECL – for provisioning under IFRS 9. The Journal of Risk Finance, 22(2), 169–190. https://doi.org/10.1108/JRF-05-2020-0094
Guo, Y., Mei, B., Rao, Y., & Ye, J. (2024). Challenges and economic consequences of IFRS 9: Evidence from China. Journal of Accounting Literature, 47(2), 298–324. https://doi.org/10.1108/JAL-06-2023-0109
Habachi, M., & El Haddad, S. (2021). Impact of Covid-19 on SME portfolios in Morocco: Evaluation of banking risk costs and the effectiveness of state support measures. Investment Management and Financial Innovations, 18(3), 260–276. https://doi.org/10.21511/imfi.18(3).2021.23
Hansen, S., Charifzadeh, M., & Herberger, T. A. (2024). The impact of IFRS 9 on the cyclicality of loan loss provisions. Journal of Corporate Accounting & Finance, 35(2), 37–49. https://doi.org/10.1002/jcaf.22669
Hegde, S. P., & Kozlowski, S. E. (2021). Discretionary loan loss provisioning and bank stock returns: The role of economic booms and busts. Journal of Banking & Finance, 130, 106186. https://doi.org/10.1016/j.jbankfin.2021.106186
Hewa, S. I., Mala, R., & Chen, J. (2020). IASB’s independence in the due process: An examination of interest groups’ influence on the development of IFRS 9. Accounting & Finance, 60(3), 2585–2615. https://doi.org/10.1111/acfi.12426
Hung, M.-C., Ching, Y.-K., & Lin, S.-K. (2021). Impact of COVID-19 on the Robustness of the Probability of Default Estimation Model. Mathematics, 9(23), 3087. https://doi.org/10.3390/math9233087
Jacobs Jr., M. (2020). A Holistic Model Validation Framework for Current Expected Credit Loss (CECL) Model Development and Implementation. International Journal of Financial Studies, 8(2), 27. https://doi.org/10.3390/ijfs8020027
Jin, Q., & Wu, S. (2023). Shifting from the incurred to the expected credit loss model and stock price crash risk. Journal of Accounting and Public Policy, 42(2), 107014. https://doi.org/10.1016/j.jaccpubpol.2022.107014
Li, X., Ng, J., & Saffar, W. (2024). Accounting-Driven Bank Monitoring and Firms’ Debt Structure: Evidence from IFRS 9 Adoption. Management Science, 70(1), 54–77. https://doi.org/10.1287/mnsc.2022.4628
López-Espinosa, G., Ormazabal, G., & Sakasai, Y. (2021). Switching from incurred to expected loan loss provisioning: Early evidence. Journal of Accounting Research, 59(3), 757–804. https://doi.org/10.1111/1475-679X.12354
López-Espinosa, G., & Penalva, F. (2023). Evidence from the adoption of IFRS 9 and the impact of COVID-19 on lending and regulatory capital on Spanish Banks. Journal of Accounting and Public Policy, 42(4), 107097. https://doi.org/10.1016/j.jaccpubpol.2023.107097
Mahieux, L., Sapra, H., & Zhang, G. (2023). CECL: Timely Loan Loss Provisioning and Bank Regulation. Journal of Accounting Research, 61(1), 3–46. https://doi.org/10.1111/1475-679X.12463
Martinelli, F., Mercaldo, F., Raucci, D., & Santone, A. (2020). Predicting Probability of Default Under IFRS 9 Through Data Mining Techniques BT - Web, Artificial Intelligence and Network Applications (Vol. 1150, pp. 959–969). https://doi.org/10.1007/978-3-030-44038-1_87
Mita, A. F., & Rahmah, N. A. (2023). Day one effect of first implementation of IFRS 9 in Indonesian banking. International Journal of Trade and Global Markets, 17(3–4), 348–354. https://doi.org/10.1504/IJTGM.2023.132057
Moscatelli, M., Parlapiano, F., Narizzano, S., & Viggiano, G. (2020). Corporate default forecasting with machine learning. Expert Systems with Applications, 161, 113567. https://doi.org/10.1016/j.eswa.2020.113567
Moscato, V., Picariello, A., & Sperlí, G. (2021). A benchmark of machine learning approaches for credit score prediction. Expert Systems with Applications, 165, 113986. https://doi.org/10.1016/j.eswa.2020.113986
Neisen, M., & Schulte-Mattler, H. (2021). The effectiveness of IFRS 9 transitional provisions in limiting the potential impact of COVID-19 on banks. Journal of Banking Regulation, 22(4), 342–351. https://doi.org/10.1057/s41261-021-00151-7
Oberson, R. (2021). The Credit-Risk Relevance of Loan Impairments Under IFRS 9 for CDS Pricing: Early Evidence. European Accounting Review, 30(5), 959–987. https://doi.org/10.1080/09638180.2021.1956985
Onali, E., Ginesti, G., Cardillo, G., & Torluccio, G. (2024). Market reaction to the expected loss model in banks. Journal of Financial Stability, 74, 100884. https://doi.org/10.1016/j.jfs.2021.100884
Ozili, P. K. (2022). Economic policy uncertainty, bank nonperforming loans and loan loss provisions: Are they correlated? Asian Journal of Economics and Banking, 6(2), 221–235. https://doi.org/10.1108/AJEB-10-2021-0119
Parnes, D. (2021). A spline hazard model for current expected credit losses. Journal of Financial Economic Policy, 14(3), 283–316. https://doi.org/10.1108/JFEP-08-2020-0175
Pastiranová, O., & Witzany, J. (2022). Does IFRS 9 Increase Volatility of Loan Loss Provisions? BT - Regulation of Finance and Accounting (pp. 243–249). https://doi.org/10.1007/978-3-030-99873-8_19
Pucci, R., & Skærbæk, P. (2020). The co-performation of financial economics in accounting standard-setting: A study of the translation of the expected credit loss model in IFRS 9. Accounting, Organizations and Society, 81, 101076. https://doi.org/10.1016/j.aos.2019.101076
Saavedra, C. A. P. B., Fachini-Gomes, J. B., Gomes, E. M. de C., & Kimura, H. (2024). Probability of default for lifetime credit loss for IFRS 9 using machine learning competing risks survival analysis models. Expert Systems with Applications, 123607. https://doi.org/10.1016/j.eswa.2024.123607
Salazar, Y., Merello, P., & Zorio-Grima, A. (2023). IFRS 9, banking risk and COVID-19: Evidence from Europe. Finance Research Letters, 56, 104130. https://doi.org/10.1016/j.frl.2023.104130
Schutte, W. D., Verster, T., Doody, D., Raubenheimer, H., & Coetzee, P. J. (2020). A proposed benchmark model using a modularised approach to calculate IFRS 9 expected credit loss. Cogent Economics & Finance, 8(1), 1735681. https://doi.org/10.1080/23322039.2020.1735681
Shi, S., Tse, R., Luo, W., D’Addona, S., & Pau, G. (2022). Machine learning-driven credit risk: A systemic review. Neural Computing and Applications, 34(17), 14327–14339. https://doi.org/10.1007/s00521-022-07472-2
Sigrist, F., & Leuenberger, N. (2023). Machine learning for corporate default risk: Multi-period prediction, frailty correlation, loan portfolios, and tail probabilities. European Journal of Operational Research, 305(3), 1390–1406. https://doi.org/10.1016/j.ejor.2022.06.035
Song, Y., Wang, Y., Ye, X., Zaretzki, R., & Liu, C. (2023). Loan default prediction using a credit rating-specific and multi-objective ensemble learning scheme. Information Sciences, 629, 599–617. https://doi.org/10.1016/j.ins.2023.02.014
Stander, Y. S. (2023). The Governance and Disclosure of IFRS 9 Economic Scenarios. Journal of Risk and Financial Management, 16(1), 47. https://doi.org/10.3390/jrfm16010047
Stander, Y. S., Verster, T., & Raubenheimer, H. (2024). A News Sentiment Index to Inform International Financial Reporting Standard 9 Expected Credit Loss Forecasts. Journal of Risk and Financial Management, 17(7), 282. https://doi.org/10.3390/jrfm17070282
Sugiarto, S., & Suroso, S. (2020). Innovation of impairment loss allowance model of Indonesian Financial Accounting Standards 71. Journal of Asian Business and Economic Studies, 27(3), 267–283. https://doi.org/10.1108/JABES-11-2019-0114
Sun, W., Zhang, X., Li, M., & Wang, Y. (2023). Interpretable high-stakes decision support system for credit default forecasting. Technological Forecasting and Social Change, 196, 122825. https://doi.org/10.1016/j.techfore.2023.122825
Xiao, J., Wang, Y., Chen, J., Xie, L., & Huang, J. (2021). Impact of resampling methods and classification models on the imbalanced credit scoring problems. Information Sciences, 569, 508–526. https://doi.org/10.1016/j.ins.2021.05.029
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Lucas Almeida Ribeiro, Beatriz Oliveira Santos, Rafael Henrique Martins, Sofía Hernández Castillo, Camila Rodríguez Navarro
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
