Stress testing retial loan portfolios with dual-time dynamics

Stress testing has become an important topic in retail lending sincethe introduction of the new Basel II guidelines. The present work uses ascenario-based forecasting approach developed explicitly for retail lendingin order to provide a suitable stress testing approach. We first decomposethe historical vintage performance data into a maturation functionof months-on-books, a quality function of vintage origination date, andan exogenous function of calendar date. In a second step, the exogenousfunction is modeled with macroeconomic data or factors representing portfoliomanagement impacts. Stress tests are performed by extrapolatingthe exogenous function using externally provided scenarios for extrememacroeconomic events. The resulting scenario is combined with the knownmaturation and quality functions. This process is repeated for each of akey set of rates, such as default rate, exposure at default, and loss givendefault in the context of Basel II. These key rate forecasts are combinedto create total portfolio forecasts and stress tests.This approach is demonstrated in an analysis of the US Mortgagemarkets.