Enhancing credit risk assessments of SMEs with non-financial information

We investigate non-financial variables for predicting bankruptcy in small and medium-sized enterprises (SMEs). The variables encompass management, board and ownership structures and are sourced from universally accessible information, rendering them available to all stakeholders and allowing for the analysis of all SMEs within a market. Using a large and recent sample of SMEs, we empirically examine the variables that predict bankruptcy over time horizons of one, two and three years. Our analysis incorporates state-of-the-art discrete hazard models, the least absolute shrinkage and selection operator (LASSO), extreme gradient boosting (XGBoost), adaptive boosting (AdaBoost), bagging and random forest. We also test robustness using balanced datasets generated using the synthetic minority oversampling technique (SMOTE). We find that including non-financial variables enhances bankruptcy predictions compared to using financial variables alone. Moreover, our results show that among our variables, the most significant non-financial predictors of bankruptcy are the age of chief executive officers (CEOs), chairpersons and board members, as well as ownership share and place of the board members’ residences.This research provides critical insights into the drivers of inflation in Ethiopia, offering policymakers a robust analysis of key economic factors influencing price stability. By identifying the money supply, exchange rate, and service sector GDP as primary inflation-augmenting variables and highlighting the counteracting roles of import volume and budget deficit, this study equips decision-makers with a focused understanding of the economic levers they can adjust to control inflation. The findings underscore the importance of adopting conservative monetary and exchange policies and promoting agricultural and industrial productivity, offering a roadmap to mitigate inflation’s adverse effects and foster sustainable economic growth in Ethiopia.