Service overview

Risk factors determination and analysis

An ongoing wave of financial crises started between 2005 and 2009, which shook world economies and resulted in a loss of billions of dollars and millions of jobs around the world. Therefore, it becomes especially important to assess and contain the damage, and to understand better how the crises will progress further. More effective regulatory mechanisms and better portfolio management practices should help achieve such goals. These tools will also help minimize the risks of such potential future meltdowns.

Even a superficial analysis of the statistical data reveals that the origination quality of US mortgage vintages started deteriorating in 2005. The US economy at the time was rather stable, with rising home prices and low unemployment rates. The worst mortgages originated in 2007. All other types of credit portfolios also showed a concurrent deterioration in quality all over the world. In most European countries, the spike in quality deterioration occurred at the end of 2008 due to an increase in bad rating practices. Such factors formed an endogenous environment for credit portfolio modeling, which is referred to as the “quality impact”.

On the contrary, the exogenous environment (that is, the “macro impact”) takes into the account such factors as macroeconomic deterioration, changes in the collection process, and seasonality. These factors started deteriorating in the US in the middle of 2006, and continued to deteriorate throughout 2009. The macroeconomic environment was at its worst at that period, with home prices falling and unemployment rising. In Europe, for most credit portfolios, the increase in external (“macro”) impact deterioration occurred at the beginning of 2009 (Jan, Feb). Its impact was also intensified by seasonal components, and the overall market picture completely eroded due to the contribution of lower-quality mortgages.

Long delays in the maturation of the likelihood of defaults (especially in mortgage loans) masked deterioration in origination quality for months or even years. This can be referred to as the “maturation impact”.

RRAS allows every pure effect from each factor to be determined separately and studied. Then a relevant forecast of behavior for each factor can be computed. Our stress-testing service, scenario analysis and forecasting are also valuable aids. The system allows to observe portfolio behavior under custom scenarios: client outflow, business development, pricing, macroeconomics...



The author presents the methods for studying credit portfolio behavior in the Modeling and Stress-Testing Credit Portfolio Behavior are partly based on so-called “dual time dynamics” method. This work suggests using dual time dynamics not for decomposing scalar values but for decomposing matrices. The author considers a credit portfolio as a process described by a first-order heterogeneous Markov chain. Starting from this premise, the author uses vintage analysis and the theorem of strong convergence of modified fixed-point algorithms to arrive at transition matrix decomposition. This method makes highly accurate forecasts of credit portfolios possible. Reserves can be estimated with excellent precision and relevant values for stress-testing obtained.

In his later article The Theory and practice of Retail Credit the author considers some successful practical applications of his methods described in the article “Credit portfolios behavior modelling and stress-test”.