The application of Data mining is becoming increasingly common in both the private and publicrnsectors. Industries such as banking, insurance, medicine, and retailing commonly use data miningrnto reduce costs, risks, and increase sales.rnForeign cogency is a scarce financial resource 111 Ethiopia. This scarcity calls for thernconsolidation and fostering of existing financial management systems to ensure optimumrnutilization of the available resource. The National Bank of Ethiopia (NBE) has the task ofrnmonitoring the settlement of importers and exporters foreign exchange commitments as per thernexisting directives. Contently in the NBE there are many importers and exporters who arerndelinquent and expected to settle their commitment.rnThus, it is the aim of this study to examine the potential applicability of data mining technologyrnin building a predictive data mining model that helps to predict potentially delinquent or nonrndelinquent importers and exporters in relation to their utilization of the foreign currency.rnTo conduct the study, the researcher adopted the Cross-Industry Standard Process for DatarnMining (CRISP-OM) process model. Several predictive classification models were built both inrndecision tree and neural network techniques using WEKA software. The best performing modelrnwas chosen by comparing the models using standard evaluation criteria such as accuracy.rnprecision, recall and interpretability.rnAccording to the evaluation results, both techniques have shown a promising performance.rnHowever, the best models for both export and import transactions were obtained using decisionrntree techniques. The decision tree approach brings about 94.02% accuracy in the case ofrnpredicting export transactions and 98.03% for import transactions. Moreover, the models built byrnthe decision tree show better results in terms of precision, recall and interpretably for bothrntransactions. Thus, compared to neural network, the decision tree approaches are more applicablernin addressing the research problem.rnAccordingly, some important rules are derived using the selected attributes such as .rnMethod of Payment, Base Of Shipment, Country-Region , Amt Of Birrln_-Range. Currency.rnValidity-period and Economic Sector that are relevant in business decision making.rnIn general, the results obtained from the stud y proved the potential applicability of data miningrntechnology to predict importers and exporters into predefined classes (delinquent and no delinquent)rnbased on their transaction characteristics.