Jul 2026· Baltic Journal of Economic Studies· Vol 12, pp. 299-311· 0 citations· 13 references
Abstract
Banking is increasingly shaped by expanding data volumes, more complex borrower behaviour, and stricter credit risk management requirements. Under such conditions, scoring models are becoming especially relevant as instruments for the formalised assessment of creditworthiness, combining analytical accuracy, speed of decision-making, and the possibility of integration into the bank’s risk management system. The study compares traditional and modern scoring models in bank credit risk management and proposes an approach to their practical use in Ukrainian banking. Its focus is on scoring models as instruments for credit risk assessment. The study combines comparative analysis, matrix modelling, simulation, statistical modelling, and machine learning methods. Given limited access to primary banking information and confidentiality requirements, the empirical analysis was conducted on a synthesised demonstration dataset designed to reflect the structure of a real retail credit portfolio. For the analysis, a sample of 1,000 observations with a default share of 22.0% was constructed, and logistic regression, discriminant analysis, Random Forest, XGBoost, and a hybrid logit + ML re-ranking model were used for comparison. The results showed that XGBoost provided the highest predictive accuracy, with an AUC-ROC of 0.861, Gini of 0.722, Recall of 0.781, and Brier score of 0.141, whereas logistic regression demonstrated an AUC-ROC of 0.781 and retained advantages in terms of interpretability and suitability for validation. The hybrid model achieved an AUC-ROC of 0.848, Gini of 0.696, Recall of 0.773, and Brier score of 0.144, thus ensuring the best balance between accuracy, explainability, calibration, and practical applicability. Practically, the study offers an adaptive approach to selecting scoring models and a matrix for evaluating them under Ukrainian banking conditions, taking into account the requirements of the regulatory environment, data quality, and the instability of the operating conditions of Ukrainian banks.
A systematic literature review of ML applications in credit risk assessment (CRA), covering publications from January 2016 to May 2026, synthesise prevailing methodologies into a unified end-to-end credit risk modelling framework spanning data preprocessing, feature engineering, model training, evaluation, and operational deployment.
Bolun Zhang, Jun Luo, Ruobing Wu et al.· Journal of Risk and Financia...· 0 citations
Regional development banks in Indonesia face increasing pressure to balance credit expansion and risk management. This study investigates the dynamics of credit risk deterioration and risk preference shifts at Bank BJB Bogor Branch during the 2020-2024 period. A qualitative descriptive approach with a case study strategy was employed, complemented by quantitative descriptive analysis. Data were collected through in-depth interviews with branch managers, credit analysts, and risk management officers, supported by internal financial reports, OJK publications, and relevant banking regulations. Risk preference was measured using the Risk Preference Index, Loan-to-Deposit Ratio, and Credit Expansion Rate, while credit risk was assessed through Non-Performing Loan ratios and Capital Adequacy Ratio. The results reveal three critical findings. First, the branch experienced a significant risk preference shift from risk neutral to risk taker category driven by aggressive credit expansion alongside declining third-party funds. Second, the MSME credit segment suffered catastrophic quality deterioration reaching an alarming non-performing level in the final observation year. Third, a structural funding vulnerability was identified as regional government deposits declined dramatically, forcing the Loan-to-Deposit Ratio to exceed the optimal threshold. The study concludes that high capital adequacy alone is insufficient to contain credit risk when aggressive expansion into high-risk segments is unsupported by proportional risk management capacity and disciplined post-disbursement monitoring.
Thiar Cnur, Herdyana, Hari Gursida· International Journal Admini...· 0 citations
This study addresses the critical challenge of credit risk assessment in data-scarce emerging and frontier markets by developing and empirically validating an enhanced eight-criterion (8C) cash-flow-centric credit scoring framework. Traditional default prediction models rely heavily on standardized financial statements and transparent accounting systems—conditions that are often absent in fragile institutional environments such as Yemen, where information asymmetry and institutional weaknesses complicate objective credit evaluation. Using a unique hand-collected dataset of 40 complete corporate credit files from the Cooperative and Agricultural Credit Bank (2010–2019), this study conducts a comparative empirical analysis between the incumbent 7C heuristic framework and the proposed 8C model. The methodology employs linear discriminant analysis and binary logistic regression to evaluate predictive accuracy, classification stability, and explanatory power within a small-sample frontier setting. The results demonstrate that the 8C model substantially outperforms the traditional 7C approach, achieving an overall classification accuracy of 92.5% compared to 77.5%, while reducing False Negative (false acceptance of defaulters) from 33.3% to 11.1%. The area under the ROC curve (AUC) increases from 0.74 to 0.94, indicating strong discriminatory power and improved risk differentiation capacity. Logistic regression results confirm that cash-flow-based repayment capacity and borrower character are the strongest predictors of default, whereas collateral shows no statistically significant explanatory power in this frontier context. The findings provide empirical support for shifting from collateral-heavy lending practices toward forward-looking, cash-flow-sensitive underwriting models aligned with IFRS 9 and Basel III principles. The study contributes theoretically, methodologically, and practically by offering a ready-to-implement framework specifically designed for data-constrained frontier banking systems and institutional environments characterized by limited financial transparency.
Waleed Yahya Mohsen Mohammed Al-Sabri· Multidisciplinary Science Jo...· 0 citations
Credit risk management is an essential function of banking institutions because it helps minimize loan defaults, protect financial assets, and ensure long-term profitability. This study examines the scope and importance of credit risk management in The South Indian Bank Ltd. by analysing credit appraisal practices, loan monitoring, borrower assessment, recovery mechanisms, regulatory compliance, and overall banking performance. The study adopted a descriptive research design using both primary and secondary data collected from 100 respondents through a structured questionnaire. Multiple Linear Regression Analysis was selected as the statistical tool to examine the influence of credit risk management practices on banking performance. The findings indicate that effective credit risk management significantly improves financial stability and operational efficiency.
Manapuram NEELA NAGALAXMI, M. Rajitha· International Journal of Cre...· 0 citations
Credit Risk Management (CRM) is essential for the stability and profitability of commercial banking institutions. This study evaluates the effectiveness of CRM practices implemented in commercial banks in Paro Dzongkhag, Bhutan. The information was collected through structured questionnaires distributed to all the relevant employees of five commercial banks located in Paro Dzongkhag. Results indicate that overall, respondents regard the CRM practices of the banks as effective; high scores were given to practices like collateral enforcement, credit limit setting and monitoring, systematic loan evaluation, and compliance with well-defined credit policies, hence showing strong pre- and post-loan supervising practices. The basic appraisal processes, such as creditworthiness assessment and regular credit scoring, were also rated positively, indicating a well-developed assessment system. On the other hand, lower ratings were observed in the areas of early warning systems aimed at detecting potential defaults, integration between credit officers and risk management units, and staff training on credit risk policies. These findings indicate that, although the institutions have strong policy underpinnings, much more remains to be done to improve proactive risk identification, interdepartmental cooperation, and continuous employee growth. In general, the paper finds that CRM practices among Paro Dzongkhag commercial banks are highly successful; however, the mitigation of the risks by the banks could be enhanced by enriching them with early warning systems, coordination procedures, and training systems, which can serve as practical recommendations to the decision makers of the commercial banks in Bhutan.
T. Phuntsho, Karma Wangchuk, Sudev Mariyil· EAST WEST JOURNAL OF BUSINES...· 0 citations
This paper examines how changes in credit risk management affected the profits of two banks in Nepal from 2020 to 2024. This study takes NABIL Bank Limited to represent a top-tier performer and Kumari Bank Limited (KBL) as a mid-tier example. The main goal was to see what happens to a bank's money when borrowers stop paying back their loans. To find out, this study analyzed four specific indicators: non-performing assets (NPAs), capital adequacy ratios (CAR), and the return on both assets (ROA) and equity (ROE). The research used basic statistical tools like correlation and regression to measure the relationship between these risk factors and the banks' earnings. The results show a very clear trend. When NPAs go up, bank profits drop fast. This proves that bad loans are the biggest enemy of profitability for these specific banks. However, the data also shows that keeping a high capital ratio helped protect the banks from these financial losses. The findings suggest that careful borrower assessment and constant loan monitoring are necessary in the Nepalese context. If these banks do not improve how they watch over their loans, their long-term stability will be at risk. These results provide basic knowledge for bankers and investors to help strengthen the commercial banking sector. The study suggests that banks in Nepal must stop focusing only on how many loans they issue and start focusing on the quality of their borrowers. Managers should use much stricter checks before approving credit. For the Nepal Rastra Bank (NRB), these results show that keeping high capital requirements is essential to safeguard the entire banking system from collapse. These findings may provide the basic knowledge for bankers, investors, and regulators to strengthen profitability and stability in commercial banks.
C. P. Adhikari· Journal of Janta Multiple Ca...· 0 citations