This research explores the application of a Vector Error Correction Model (VECM) in forecasting Default Rates, using key macroeconomic indicators such as Gross Domestic Product, inflation and unemployment rates. The VECM was selected due to its ability to deal with non-stationary cointegrated variables, allowing it to capture both the short-term dynamics and the long-term equilibrium relationships between the variables. The forecasted Default Rate is a critical variable in the estimation of the Variable Scalar Approach. Under IFRS 9, this approach adjusts Through-the-Cycle Probabilities of Default into Point-in-Time Probabilities of Default, allowing the inclusion of forwardlooking macroeconomic indicators in the Probability of Default estimate, thereby enhancing financial institutions' ability to estimate Expected Credit Losses and internal capital requirements. The study finds that the VECM provided reasonably accurate forecasts for default rates during the period considered, with minimal deviations from the observed data, all within an acceptable range. While diagnostic tests confirmed the model's robustness and reliability, limitations were observed in its ability to predict extreme economic events, particularly during financial crises such as those of 2009 and 2020. To address this limitation, a worst-case scenario is incorporated into the scalar factor calculation. Despite these challenges, the model has proven to be a valuable tool for enhancing credit risk management.

info:eu-repo/semantics/publishedVersion