A hybrid rough–grey methodology for inferring the bank branch grades under future uncertainty
Abstract
The grading of bank branches is a costly and time-consuming auditing procedure that requires the evaluation of multiple qualitative and quantitative criteria. This study proposes a data-driven decision-support framework for extracting decision rules under uncertainty and applying them to infer the future grade of each branch based on selected performance indicators. In the first stage, the branch grading results obtained over a five-year period are treated as the decision attribute, while the corresponding financial indicators are used as condition attributes within the Rough Set Theory framework. This stage identifies the most accurate rule-based classification model and determines its reduct as the most relevant subset of indicators for branch grading. In the second stage, the future values of the selected indicators are forecasted for the subsequent two years. Given the limited size of the available data, several grey forecasting models are employed and compared. Finally, the decision rules extracted in the first stage are applied to the forecasted indicator values to infer the future grades of bank branches with high accuracy, thereby reducing dependence on extensive and time-consuming auditing procedures. The findings demonstrate that combining Rough Set Theory with Grey forecasting models offers an effective predictive and knowledge-based decision-support tool for evaluating branch performance in dynamic and uncertain environments. The proposed framework can support banking managers and policymakers in performance assessment, branch network reorganization, strategic planning, and evidence-based decision-making.