Bankruptcy Prediction Using Machine Learning Techniques

In this study, we apply several advanced machine learning techniques including extreme gradient boosting (XGBoost), support vector (SVM), and a deep neural network to predict bankruptcy using easily obtainable financial data of 3728 Belgian Small Medium Enterprises (SME’s) during the period 2002–2012. Using above-mentioned techniques, bankruptcies with global accuracy 82–83% only three ratios: return on assets, current ratio, solvency ratio. While prediction is similar previous models in literature, our model very simple implement represents an accurate user-friendly tool discriminate between bankrupt non-bankrupt firms.