Predicting the Probability of Bankruptcy of Service Sector Enterprises Based on Ensemble Learning Methods

Abstract

This chapter focuses on developing an automated model for predicting the bankruptcy of trading enterprises. Due to the COVID-19 pandemic, many companies have suffered significant financial losses and continue to struggle with its negative consequences. This has resulted in an acute need for financial resources, making it crucial for credit organizations to enhance their credit scoring procedures. The chapter explores ensemble methods for predicting bankruptcy, including random forest, gradient boosting trees, and tree ensemble. By utilizing these methods, the researchers aim to improve the accuracy of bankruptcy predictions and provide credit organizations with a reliable tool for assessing the financial stability of trading enterprises. Given the current economic situation, the development of such an automated model has become more important than ever. By implementing these ensemble methods, credit organizations can make more informed decisions regarding lending and investment, which can have a significant impact on the stability of the financial market.