Bankruptcy Prediction Using a GAN-based Data Augmentation Hybrid Model

Abstract

In order to lower the danger of a company failing, research in the area of bankruptcy prediction is still being done. New effective models are being developed employing a variety of cutting-edge methodologies. However, majority of bankruptcy databases are unbalanced and may include unnecessary data. So, creating a powerful, trustworthy model to improve prediction is always a difficult undertaking. In this paper, we made the forecast in three stages. In the first stage, we concentrated on balancing the datasets using two well-known methods, SMOTETomek and Generative Adversarial Network (GAN), which generate synthesized data. Then, in the second phase, a selection of pertinent features was extracted using three wrapper-based feature selection methods and five filter methods. Three models namely ANN, CNN, and LSTM have been used for the third step of actual prediction. After obtaining pertinent information by feature selection from both sampling approaches, the results show that the ANN model has a better capacity for prediction than the other two predictive models. It has been demonstrated that GAN technique outperforms the SMOTETomek with respect to all three predictive models. Among the filter methods, the chi-square test gives better prediction results, whereas, among wrapper methods, backward elimination gives better results.