Macroeconomic Determinants of Loan Portfolio Credit Risk in Banks

The credit risk is one of the main risks in commercial banks and the ability to manage it meaningly affects banks' stability. This risk arises due to the particular reasons related to the possibility to lose loans if the debtors are not able to meet their financial obligations. When making the decisions of financing the loan applicants, banks use the credit risk assessment models that allow estimating the probability of the potential borrowers to default on their loan commitments. The main goal of managing the credit risk in banks is to compound the loan portfolio of the acceptable risk level. According to Derelioglu and Gurgen (2011) the credit risk analysis aims to decrease future losses by estimating the potential risk and eliminating the new credit proposal if the risk is higher than a defined tolerance value. In this respect, it is essential to identify the main factors causing this risk in order to manage it. When assessing the credit risk of every company, banks usually analyze the financial data and some qualitative factors as the independent variables in the statistical credit risk assessment models. But in changing the credit policy in banks and pricing the credits, it is very important to predict the quality of loan portfolio in future. The problem can be summarized as finding the statistical methods that relates the proportion of doubtful and non-performing credits in the loan portfolio (dependent variable) with the set of explanatory variables (macroeconomic information of a country). The aim of this research is to find the macroeconomic determinants that significantly influence the changes of loan portfolio credit risk in banks and to develop the statistical model for prediction of the proportion of doubtful and non-performing loans. The scientific literature analysis results confirmed the influence of macroeconomic conditions on credit risk of debtors in banks and presented that the changes in quality of loan portfolio in banks depend on GDP, inflation, interest rates, money supply, industrial production index, current account balance and other. In empirical research 22 EU countries were grouped into 3 clusters according to their similarity in changes of the doubtful and non-performing loans percentage in banks. The set of 20 independent variables as factors determining the changes in amount of doubtful and non-performing loans was created. These variables were calculated from 9 macroeconomic indicators of 3 years. The model was developed to classify the countries into clusters applying the logistic regression, factor analysis and probit methods. The classification accuracy is 100 %. The predictions of doubtful and non-performing loans indexes are based on the analysis of the scores of extracted 5 factors as new independent variables. The multiple regression and polynomial regression methods were applied for the index predictions in clusters. The developed model in this research enables to predict the percentage of doubtful and non-performing loans in banks with the average 98,06% accuracy. The research has confirmed that the amount of doubtful and non-performing loans in banks highly depends on macroeconomic changes in a country. The model can warn the banks in advance if the significant increase in the loan portfolio credit risk after 2 years is highly possible.