Evaluating the Predictive Efficiency of the CAGEX-Rating System in Managing Bank Credit Risks: Evidence from Algerian Small and Medium Enterprises
الكلمات المفتاحية:
Credit Risk Rating، Cagex Rating Model، Binary Logistic Regression، Algerian Firms، Default Probabilityالملخص
This study aimed to test the predictive power of the local credit rating model “Cagex Rating" within the Algerian banking sector, employing the binary logistic regression method. The study sample included 65 economic firms (both sound and defaulting) operating in various sectors, based on a set of quantitative variables (debt-to-equity ratio) and qualitative variables (credit history,management quality, and business diversification). The study concluded that the model demonstrated high discriminatory efficiency and significant discriminatory ability among firms, with a correct classification rate exceeding 95% and robust goodness-of-fit indicators. The results also demonstrated the important role played by qualitative variables,particularly credit history, management competence, and business diversification, as decisive factors in explaining the probability of default in the Algerian banking sector. الملخص هدفت هذه الدراسة إلى اختبار القدرة التنبؤية لنموذج التصنيف الائتماني المحلي «Cagex Rating» في القطاع البنكي الجزائري، باستخدام طريقة الانحدار اللوجستي الثنائي. وشملت عينة الدراسة 65 شركة اقتصادية (سليمة ومتعثرة على حد سواء) تعمل في قطاعات مختلفة، استنادًا إلى مجموعة من المتغيرات الكمية (نسبة الدين إلى حقوق الملكية) والمتغيرات النوعية (السجل الائتماني، وجودة الإدارة، وتنويع الأنشطة التجارية). وخلصت الدراسة إلى أن النموذج أظهر كفاءة تمييزية عالية وقدرة تمييزية كبيرة بين الشركات، بمعدل تصنيف صحيح تجاوز 95٪ ومؤشرات قوية لمدى ملاءمة النموذج. كما أظهرت النتائج الدور المهم الذي تلعبه المتغيرات النوعية — لا سيما السجل الائتماني وكفاءة الإدارة وتنويع الأعمال كعوامل حاسمة في تفسير احتمالية التخلف عن السداد في القطاع المصرفي الجزائري.المراجع
Adesanya, M. E. (2024). Assessing Credit Risk through Borrower Analysis to Minimize Default Risks in Banking Sectors Effectively. International Journal of Research Publication and Reviews, 5(12), 5479–5493. https://doi.org/10.55248/gengpi.5.1224.0233
BCBS, B. C. on B. S. (2017). Comité de Bâle sur le contrôle bancaire Bâle III : finalisation des réformes de l ’ après-crise.
Bekhet, H. A., & Eletter, S. F. K. (2014). Credit risk assessment model for Jordanian commercial banks: Neural scoring approach. Review of Development Finance, 4(1), 20–28. https://doi.org/10.1016/j.rdf.2014.03.002
Cagex. (n.d.-a). CAGEX-Rating Scale. Retrieved February 20, 2026, from https://www.cagex.dz
Cagex. (n.d.-b). Content and Mechanisms of the ‘CAGEX-Rating’ Model. https://www.cagex.dz
Cagex. (n.d.-c). How to Set Up Analysis Networks and Operational Mechanisms. https://www.cagex.dz
Chen, G., Busababodhin, P., & Chutiman, N. (2024). Credit Risk Analysis of Micro and Small Enterprises Based on Big Data-Driven Logistic Regression Models of Bank Credit Records. ACM International Conference Proceeding Series, April 2024, 1182–1186. https://doi.org/10.1145/3671151.3671357
Committee, B., & Supervision, on B. (2001). The Internal Ratings Based Approach. In International Regulation of Banking (Issue May). https://doi.org/10.1093/law/9780199643981.003.0010
Dhima, J. (2020). Évolution des méthodes de gestion des risques dans les banques sous la réglementation de Bale III : une étude sur les stress tests macroprudentiels en Europe. Action Publique, N° 6(1), 30–30. https://doi.org/10.3917/aprp.006.0030
Dudian Monica, B. maciuca. (2009). INTERNAL RATINGS SYSTEMS: AN EMPIRICAL APPROACH. Studies in Business and Economics, 71–79. https://www.researchgate.net/publication/46513452
Fakhari, F., & Yah, S. (2019). The Importance of Using Statistical Models in the Early Detection of Credit Defaults in Banks -An Analytical Study. The Journal of North African Economies, 15(21), 361–382.
Fathy, K., Marie, M., & Yehia, E. (2024). An Intelligent Model to Assess the Credit Risk in Egyptian Banks. Scientific Journal for Financial and Commercial Studies and Research, 38(1), 1749–1782. https://doi.org/10.21608/sjrbs.2024.272113.1637
Gliz, A., & Touati-Tliba, M. (2012). Estimation du risque de crédit et qualité de l’information comptable en Algérie. Les Cahiers Du Cread, 5–29.
Kowsar, M. M. (2022). a Systematic Review of Credit Risk Assessment Models in Emerging Economies: a Focus on Bangladesh’S Commercial Banking Sector. American Journal of Advanced Technology and Engineering Solutions, 02(01), 01–31. https://doi.org/10.63125/p7ym0327
Liliana Rojas-Suarez. (2001). RATING BANKS IN EMERGING MARKETS : What Credit Rating Agencies Should Learn From Financial Indicators Liliana Rojas-Suarez Visiting Fellow.
Matoussi, H., & Abdelmoula, A. K. (2010). LA PREVENTION DU RISQUE DE DEFAUT DANS LES BANQUES TUNISIENNES : Analyse comparative entre les méthodes linéaires classiques et les méthodes de l ’ intelligence artificielle : les réseaux de neurones artificiels. Crises et Nouvelles Problématiques de La Valeur., 1–30. - 61 -
Nwachukwu, P. S., Chima, O. K., & Harriet Okolo, C. (2025). Credit Risk Assessment Models in Commercial Banking: Approaches, Evolution, and a Proposed Hybrid Risk Evaluation Framework. Engineering and Technology Journal, 10(09), 7040–7063. https://doi.org/10.47191/etj/v10i09.22
Omrani, T., Tahri, S., & Messaoudi, R. (2023). Analysis and management of credit risk in Algerian commercial banks : An attempt to develop a practical risk assessment model to improve banking performance. The Journal of Contemporary Issues in …, 29(04). https://doi.org/10.47750/cibg.2023.29.04.002
Ou, L. (2025). Research on Credit Risk Evaluation System for Small and Medium-Sized Enterprises Based on Machine Learning Model. SHS Web of Conferences, 218, 02016. https://doi.org/10.1051/shsconf/202521802016
Oukil, N., & Ben Khaled, O. (2013). The Use of Logistic Regression as a Modern Method for Measuring Credit Risk—A Field Study of the Bank for Agriculture and Rural Development (Algeria). MAAREF (Revue Académique ) Partie Sciences Économiques, 8(15), 31–48.
Shittu, A. K. (2022). Advances in AI-driven credit risk models for financial services optimization. International Journal of Multidisciplinary Research and Growth Evaluation, 3(1), 660–676. https://doi.org/10.54660/.ijmrge.2022.3.1-660-676
Wagdi, O., & Tarek, Y. (2022). The Integration of Big Data and Artificial Neural Networks for Enhancing Credit Risk Scoring in Emerging Markets: Evidence from Egypt. International Journal of Economics and Finance, 14(2), 32. https://doi.org/10.5539/ijef.v14n2p32
ZIBANI, F. (2018). Notation Financière et Scoring : Application dans le secteur financier algérien Devant. Université M’hamed Bouguara de Boumerdes.
