Abstract

Forecasting bank failures has been an essential study in the literature due to their significant impact on the economic prosperity of a country. Acting as an intermediary player, banks channel funds from those with surplus capital to those who require capital to carry out their economic activities. Therefore, it is essential to generate early warning systems that could warn banks and stakeholders in case of financial turbulence. In this paper, three machine learning models named as GLMBoost, XGBoost, and SMO were used to forecast bank failures. We used commercial bank failure data of Turkey between 1997 and 2001, where we have 17 failed and 20 healthy banks. Our results show that the Sequential Minimal Optimization and GLMBoost provide the same performance when classifying failed banks, while GLMBoost performs better in AUC and SMO when considering total classification success. Lastly, XGBoost, one of the most recent and robust classification models, surprisingly underperformed in all three metrics we used in research.

Highlights

  • 1 Commercial banks are one of the most important pillars of an economy in a country

  • Our results show that the Sequential Minimal Optimization and GLMBoost provide the same performance when classifying failed banks, while GLMBoost performs better in AUC and SMO when considering total classification success

  • After a series of preexperiments where we tried to find out the best classifiers to proceed with this research, we concluded that Sequential Minimal Optimization, GlmBoost, and XGBoost were the top predictors

Read more

Summary

Introduction

1 Commercial banks are one of the most important pillars of an economy in a country. They play a vital role in being an intermediary actor by maintaining efficient monetary transactions between creditors and debtors. Unfortunate events in the banking sector affect the economy as a whole. The CAMELS rating system is used to assess the financial ability of a bank. It measures the ratios of capital adequacy, assets, management capability, earnings, liquidity, and sensitivity. Banks are scaled between ‘I’ to ‘V’, while ‘I’ implies that banks' performance is robust, ‘V’ implies that the bank is fundamentally unsound

Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call