Assessment Of The Bank's Credit Risk Control From Economic Uncertainties: Bank Crisis Early Warning System

Abstract

The Bank faces many risks in its business activities, ranging from the risk of large withdrawals by savers (liquidity risk), the risk associated with investments in securities products (commercial risk) and the risk of not being able to recover loans (credit risk). This study will assess a type of banking risk, which is credit risk, through a variable representative of the rate of non – performing loans, the research data is macro data of 15 countries of the European Union (EU) over the period of 2000 to 2021 to find out the impact of macro factors such as economic growth, inflation rate, unemployment rate, etc. on the bank's credit risk in economic instability events such as the financial crisis and the Covid - 19 pandemic. The article uses the method of dynamic panel data and S.GMM regression model for analysis and evaluation. The study is motivated by the hypothesis that the two macroeconomic variables can have an effect on the quality of bank loans. Furthermore, in order to reduce bank credit risks and provide early warning systems in case of banking crisis, the article will consider using Random Forest and Classification Tree machine learning models to build and develop systems.