Purpose This study aims to develop an interpretable and data-driven framework for grading bank branches under economic uncertainty and inflation, and to apply the extracted decision rules to regrade branches using new data, independent of the bank’s official classification system. Design/methodology/approach Key performance indicators were identified based on expert judgment and used as the basis for branch grading. Rough Set Theory was applied to observed branch performance data to extract transparent decision rules and identify relationships between financial indicators and final grades. To ensure the applicability of these rules to new and evolving economic conditions, financial indicators were updated using a grey forecasting model, enabling alignment between the base period and subsequent data. The updated indicators were then evaluated using the extracted rules to obtain revised branch grades. Findings The integrated Rough Set and Grey forecasting framework demonstrates strong performance in analyzing and predicting branch grades in inflationary and uncertain economic environments, achieving high predictive accuracy while maintaining interpretability of the decision rules. Originality/value This study proposes a transparent and interpretable decision-support tool that assists banking policymakers and managers in regrading branches using updated data. The framework supports branch network restructuring, performance-based policy formulation, and strategic planning in uncertain and inflationary contexts. The combined use of Rough Set Theory and Grey forecasting provides a practical and novel approach to rule-based bank branch evaluation under economic uncertainty.
Ahmadian et al. (Thu,) studied this question.