Credit Line Exposure at Default Modelling Using Bayesian Mixed Effect Quantile Regression

Abstract For banks, credit lines play an important role exposing both liquidity and risk. In the advanced internal ratings-based approach, banks are obliged to use their own estimates of exposure at default using conversion factors. volatile segments, additional downturn required. Using world's largest database defaulted from US Europe macroeconomic variables, we apply a Bayesian mixed effect quantile regression find strongly varying covariate effects over whole conditional distribution factors especially between United States Europe. If variables do not provide adequate estimates, model is enhanced by random effects. Results European suggest that high driven rather than observable covariates. We further show impact economic surrounding highly depends on level utilization one year prior default, suggesting with drawdown potential most affected downturns hence bear highest risk in crisis periods.