Tail Risk Modeling with Copulas

In this article we present the motivation and methodology behind the Tail Risk Model for Equities. This model provides portfolio managers with reports on tail risk measures, such as VaR and Expected Shortfall in a non‐normal setting, and attributes risk to individual securities and factors. We show in detail how copulas, heavy‐tailed distributions and a sector‐wise decomposition of the equities universe are combined in a Monte‐Carlo simulation to evaluate tail risk. A discussion of the out‐of‐sample testing procedure used for model selection is also provided