Rising volumes of non-performing loans (NPLs) remain one of the most persistent threats to financial stability in emerging banking systems, where credit registries are thin, macroeconomic volatility is elevated, and conventional scorecards rely on linear discriminant or logistic specifications that struggle to capture non-linear interactions among borrower, loan, and macroeconomic risk factors. This study benchmarks four supervised machine learning classifiers — logistic regression, random forest, gradient boosting, and extreme gradient boosting (XGBoost) — in predicting twelve-month-ahead loan delinquency using a loan-level panel drawn from commercial banks operating in an emerging Central Asian banking system over 2019–2025. Models are trained on borrower, loan, and collateral characteristics together with a macroeconomic overlay, validated through five-fold cross-validation with chronological hold-out testing, and compared using AUC-ROC, the Gini coefficient, the Kolmogorov-Smirnov (KS) statistic, F1-score, and Brier score. The results show that tree-based ensembles substantially outperform the logistic baseline, with XGBoost achieving the highest discriminatory power, and that augmenting loan-level features with macroeconomic overlay variables materially improves out-of-sample predictive accuracy. Feature-importance analysis identifies delinquency history, debt-service-to-income ratio, collateral coverage, and sectoral exposure as the dominant predictors. The findings offer commercial banks and supervisory authorities in emerging markets an empirically validated architecture for early-warning credit scoring capable of narrowing the gap between reported and risk-based measures of asset quality.
Djamalov Gofir Oribjanovich· EPRA International Journal o...· 0 citations
This study develops a dynamic panel econometric framework to quantify the structural impact of macroeconomic conditions on the non-performing loan (NPL) ratios of commercial banks across a panel of twenty-eight emerging market economies observed between 2010 and 2024. Addressing dynamic persistence and the endogeneity inherent in the joint determination of credit quality and macro-financial conditions, the empirical strategy combines a two-step System Generalized Method of Moments (System GMM) estimator with a Panel Autoregressive Distributed Lag (P-ARDL) error-correction specification estimated via Pooled Mean Group (PMG). The results confirm strong dynamic persistence in NPL ratios and show that real GDP growth, the unemployment rate, consumer price inflation, and the real lending rate are statistically significant macroeconomic drivers of asset-quality deterioration. Critically, the interaction between currency depreciation and the share of unhedged foreign-currency lending is found to amplify the NPL response to exchange-rate shocks, a channel of particular relevance to partially dollarized banking systems in transition economies such as Uzbekistan, where reported and risk-based measures of asset quality have been shown to diverge materially. The error-correction estimates indicate that approximately one-third of any disequilibrium between actual and long-run equilibrium NPL levels is corrected within a single year. These findings offer a structural basis for calibrating countercyclical provisioning and macroprudential buffers in emerging banking systems exposed to currency and business-cycle volatility.
Djamalov Gofir Oribjanovich· EPRA International Journal o...· 0 citations