Scenario Analysis in the Measurement of Operational Risk Capital: A Change of Measure Approach

Operational risk is now increasingly being considered an important financial risk and has been gaining importance similar to market and credit risk. In particular, in the banking regulation for large financial institutions it is required that operational risk be separately measured. The capital being held to safeguard against such risk is very significant at a large financial institution. As our understanding of such risk is evolving so are the methodologies for measuring such risk. While scenario analysis is an important tool for financial risk measurement, its use in the measurement of operational risk capital has been quite arbitrary and often inaccurate. The importance of scenario analysis cannot be overstated. The Federal Reserve System used scenarios to stress test the risk exposures of a financial institution during a recent financial crisis. We propose a method for the measurement of operational risk exposure of an institution using scenario analysis and internal loss data. Using the Change of Measure approach used for asset pricing in financial economics we evaluate the impact of each scenario in the total estimate of the operational risk capital. We show that the proposed method can be used in many situations, such as the calculation of operational risk capital, stress testing, and what-if assessment for scenario analysis. By using this method one could also generate a key ingredient that is a precursor toward creating a catastrophe bond on various segments of operational risk exposures of an institution. Although the method described here is in the context of operational loss, it can be used in modeling scenarios in many other contexts, such as insurance pricing, marketing forecast, and credit evaluations.