Incorporating Individual Retail Loan Data into the Macro Stress Testing Framework

Macro stress testing has become an increasingly important part of central banks’, and macroprudential authorities’ toolkits after the global financial crises. Estimation of credit risk losses under adverse circumstances is one of the most important parts of the stress testing framework within the EU/Euro area. However, standard satellite models based on econometrics of time series may not be well suited for countries with short time series or an incomplete credit cycle. This paper shows how to incorporate microdata into the stress testing framework. The paper uses a unique set of individual retail loan data available to the NBS with a large number of data items provided for each loan. The new framework using micro data yields to a much larger increase of NPLs than using time series data in the case of Slovakia. On the other hand, overall losses estimated under the adverse scenario are comparable to losses estimated using the previous framework. Last but not least, the new framework using micro data enables us to estimate the change in risk weights caused by the adverse scenario as well.