Modeling Correlations in Operational Risk

The key demand for banks' economic capital methodology is to ensure that the model covers all relevant sources of risk in the right way. Operational risk models treat the arising losses as stochastic variables. One of the problems encountered in modeling is the need of taking into account correlations between events. It is possible to build models for correlated events based on copula functions. But the problem is that the losses are related to isolated events and simple applications of copulas are not allowed. The authors present a new algorithm that shows a modified application of copulas to calculating operational risk. The calculations were done on real data that allows for examining the correlation impact on risk measurement. As an additional evaluation of the algorithm a reference model based on the Pareto-Lévy copulas was used.