Service overview


Figure 3. Risks can result in unforeseen losses.

Risk management is crucial for a bank that wants to effectively compete in the context of challenging market conditions. What the most significant risks a bank specializing in individual credit faces? We consider them to be loan risk, market risk and strategy risk.

Loan risk is unforeseen losses, usually from some external factors such as an economic crisis. How can a business be made safe from a sudden macroeconomic downturn? There is no silver bullet, but some can significantly reduce loan risk. For instance, it is well-known that the Russian economy is exports-oriented, with a large portion of the country’s GDP coming from oil and gas sales. Energy prices are strongly correlated with unemployment here. Loan risk would be hedgeable with oil options, but that would require a highly accurate model for predicting credit portfolio behavior. RRAS modeling is up to the challenge. We have developed a special service for finding optimal ways to hedge loan risks through options.

Market risk revolves around interest risk, funding cost and liquidity risk. When interest risk decreases, liquidity risk or funding cost may increase. A rate spike will bring up funding cost, which leads to losses, hence market risk. This risk can be minimized by using a liquidity cushion, which is to say, long money. The question is, how to optimize this process? RRAS’ hedging service succeeds here as well.

Strategy risk comes from bad decisions on managerial top. For example, a manager guided by negative news may decide to halt disbursement. This will of course lower loan and market risks, but inevitably shrink the portfolio and business itself. In the end lost profits can be really significant so that the possible losses in the context of market and credit risks materialization can outweigh any gains from risk reduction. Strategic decision optimization is a unique RRAS service.



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”.