Dimakos, Xeni Kristine; Aas, Kjersti
Statistical Modelling, vol. 4, 2004
In this article, we present a new approach to modelling the total economic capital required to protect a financial institution against possible losses. The approach takes into account the correlation between risk types, and in this respect, it improves upon the conventional practice that assumes perfectly correlated risks. A statistical model is built, and Monte Carlo simulation is used to estimate the total loss distribution. The methodology has been implemented in the Norwegian financial group DnB’s system for risk management. Incorporating current expert knowledge of relationships between risks, rather than taking the most conservative stand, gives a 20% reduction in the total economic capital for a one year time horizon.