Liquidity–credit risk dynamics and bank profitability: hybrid econometric and machine learning evidence from MENA

Purpose This study aims to investigate the interplay between liquidity risk, credit risk and bank profitability in the Middle East and North Africa (MENA) region, a context marked by macroeconomic volatility and regulatory heterogeneity. Specifically, this research explores the dual role of credit risk as both a mediating and moderating variable in the relationship between liquidity risk and bank performance. Design/methodology/approach A balanced panel of listed commercial banks across MENA from 2015 to 2023 is analyzed using a stepwise two-step system generalized method of moments approach. This technique addresses endogeneity, simultaneity and dynamic panel bias while allowing for robust inference on mediating and moderating effects. To complement this, a suite of supervised machine learning (ML) models – including random forest, Extreme Gradient Boosting, support vector machines (SVMs) and LASSO – is used to uncover complex nonlinear interactions and enhance predictive performance. Findings Empirical results confirm that liquidity risk significantly impairs bank profitability, as measured by return on assets, return on equity and net interest margin. Credit risk exhibits a statistically significant mediating effect by transmitting liquidity constraints into reduced asset quality. Moreover, moderation analysis reveals that the profitability impact of liquidity risk is amplified in banks with elevated credit risk levels. ML models substantiate these findings, with interaction-based specifications yielding the best predictive performance. Originality/value This study bridges a critical gap in the literature by examining interconnected risk dynamics within the underexplored MENA banking landscape. It offers both methodological innovation through the fusion of econometric and AI techniques and theoretical advancement by validating the dual role of credit risk. The findings hold actionable implications for policymakers, bank executives and regulators seeking integrated risk governance frameworks in emerging markets.

Institutions

Publication Details

Journal
Journal of financial reporting & accounting
Published
2025-10-23
DOI
https://doi.org/10.1108/jfra-04-2025-0291
Citations
2
Primary Topic
Financial Distress and Bankruptcy Prediction
Type
article
Field-Weighted Citation Impact
7.82
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Liquidity–credit risk dynamics and bank profitability: hybrid econometric and machine learning evidence from MENA

2 citations
Journal of financial reporting & accounting
Financial Distress and Bankruptcy Prediction
7.82
article

Liquidity–credit risk dynamics and bank profitability: hybrid econometric and machine learning evidence from MENA

article en
2 citations

Abstract

Purpose This study aims to investigate the interplay between liquidity risk, credit risk and bank profitability in the Middle East and North Africa (MENA) region, a context marked by macroeconomic volatility and regulatory heterogeneity. Specifically, this research explores the dual role of credit risk as both a mediating and moderating variable in the relationship between liquidity risk and bank performance. Design/methodology/approach A balanced panel of listed commercial banks across MENA from 2015 to 2023 is analyzed using a stepwise two-step system generalized method of moments approach. This technique addresses endogeneity, simultaneity and dynamic panel bias while allowing for robust inference on mediating and moderating effects. To complement this, a suite of supervised machine learning (ML) models – including random forest, Extreme Gradient Boosting, support vector machines (SVMs) and LASSO – is used to uncover complex nonlinear interactions and enhance predictive performance. Findings Empirical results confirm that liquidity risk significantly impairs bank profitability, as measured by return on assets, return on equity and net interest margin. Credit risk exhibits a statistically significant mediating effect by transmitting liquidity constraints into reduced asset quality. Moreover, moderation analysis reveals that the profitability impact of liquidity risk is amplified in banks with elevated credit risk levels. ML models substantiate these findings, with interaction-based specifications yielding the best predictive performance. Originality/value This study bridges a critical gap in the literature by examining interconnected risk dynamics within the underexplored MENA banking landscape. It offers both methodological innovation through the fusion of econometric and AI techniques and theoretical advancement by validating the dual role of credit risk. The findings hold actionable implications for policymakers, bank executives and regulators seeking integrated risk governance frameworks in emerging markets.

Journal of financial reporting & accounting
Egypt-Japan University of Science and Technology (EG)
Decent work and economic growth
Openalex Percentile: Top 3%
Financial Distress and Bankruptcy Prediction
7.82
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Liquidity–credit risk dynamics and bank profitability: hybrid econometric and machine learning evidence from MENA · Journal of financial reporting & accounting (2025) | TGRS Research Map | TGRS