Personal bankruptcy prediction using machine learning techniques

Abstract

It has become crucial to have an early prediction model that provides accurate assurance for users about the financial situation of consumers. Recent studies focused on predicting corporate bankruptcies and credit defaults, not personal bankruptcies. Due to that, this study fills the literature gap by comparing different machine learning algorithms to predict personal bankruptcy. The main objective of the study is to examine the usefulness of machine learning models such as random forest, XGBoost, LightGBM, AdaBoost, CatBoost, and support vector machines in forecasting personal bankruptcy. The research relies on two samples of households (learning and testing) from the Survey of Consumer Finances, which was conducted in the United States. Among the estimated models, CatBoost and XGBoost showed the highest effectiveness. Among the most important variables used in the models are income, refusal to grant credit, delays in the repayment of liabilities, the revolving debt ratio, and the housing debt ratio.