Corporate Bankruptcy Prediction Using Machine Learning Methodologies with a Focus on Sequential Data

• Published in: Computational economics Vol. 59; no. 3; pp. 1231 - 1249
• Main Authors: Kim, Hyeongjun, Cho, Hoon, Ryu, Doojin
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.03.2022; Springer Nature B.V
• Subjects: Algorithms; Bankruptcy; Behavioral/Experimental Economics; Classification; Computer Appl. in Social and Behavioral Sciences; Credit risk; Discriminant analysis; Economic Theory/Quantitative Economics/Mathematical Methods; Economics; Economics and Finance; Machine learning; Macroeconomics; Math Applications in Computer Science; Methods; Neural networks; Neurons; Operations Research/Decision Theory; Performance indicators; Recurrent; Recurrent neural networks; Research methodology; Short term memory; Statistical analysis; Support vector machines; Variables; Recurrent neural network; G33; Classification; Machine learning; Bankruptcy prediction; Long short-term memory; G12; G17
• ISSN: 0927-7099; 1572-9974
• DOI: 10.1007/s10614-021-10126-5

We examine whether corporate bankruptcy predictions can be improved by utilizing the recurrent neural network (RNN) and long short-term memory (LSTM) algorithms, which can process sequential data. Employing the RNN and LSTM methodologies improves bankruptcy prediction performance relative to using other classification techniques, such as logistic regression, support vector machine, and random forest methods. Because performance indicators, such as sensitivity and specificity, differ depending on the methodology, selecting a model that suits the purpose of the bankruptcy predictions is necessary. Our ensemble model, a synthesis of all methodologies, exhibits the best forecasting performance. In the test sample for the ensemble model, none of the observations with a default probability of less than 10% defaults within one year.