Bankruptcy Prediction Using Bi-Level Classification Technique

Abstract

Bankruptcy is a legal proceeding involving a person or a business, where they are unable to pay the debt. Financial investors, banks, money lenders, and the government seek to know the status of bankruptcy of firms as it carries huge financial risk. The prediction of bankruptcy will help all the stakeholders of the company. To model bankruptcy prediction, traditional statistical methods like multiple discriminant analysis and Machine Learning (ML) models like Decision Trees, Support Vector Machines, and Ensemble have been utilized. In existing works, homogeneous base estimators are used while developing ensemble algorithms. This study uses a bi-level classification technique (a heterogeneous ensemble ML technique) to predict bankruptcy. To train the classifier, the features extracted are Altman z-score parameters and market-based measures. Unlike previous studies, this study uses an indicator of corporate governance as a feature. The outcome of this study is an improvement in the performance of the ML model using the bi-level classification technique. An F1-score of 0.98 and 97.8% accuracy is achieved with features including Tobin’s Q and bi-level classification technique as an ML model. It outperforms the 96% accuracy of the random forest algorithm.