A comparative analysis of machine learning techniques for imbalanced data

This study compares the predictive accuracy of a set of machine learning models coupled with three resampling techniques (Random Undersampling, Random Oversampling, and Synthetic Minority Oversampling Technique) in predicting bank inactivity. Our sample includes listed banks in EU-28 member states between 2011 and 2019. We employed 23 financial ratios comprising capital adequacy, asset quality, management capability, earnings, liquidity, and sensitivity indicators. The empirical findings established that XGBoost performs exceptionally well as a classifier in predicting bank inactivity, particularly when considering a one-year time frame before the event. Furthermore, our findings indicate that random forest with Synthetic Minority Oversampling Technique demonstrates the highest predictive accuracy two years prior to inactivity, while XGBoost with Random Oversampling outperforms other methods three years in advance. Furthermore, the empirical results emphasize the significance of management capability and loan quality ratios as key factors in predicting bank inactivity. Our findings present important policy implications. Bank inactivity predictive accuracy of machine learning techniques with resampling techniques is analyzed.Data on banks in the EU-28 member states between 2011 and 2019 are used.XGBoost performs exceptionally well one year before inactivity.Random Forest with Synthetic Minority Oversampling is the best classifier two years before inactivity.XGBoost with Random Oversampling outperforms other methods three years before inactivity.