Vine Copula based portfolio level conditional risk measure forecasting

TL;DR

This paper introduces a vine copula-based method combined with ARMA-GARCH models to improve portfolio risk measure forecasting by capturing complex dependencies and stress scenarios, demonstrated through a case study on Spanish equities.

Contribution

It presents a novel combination of vine copulas with univariate ARMA-GARCH models for conditional risk forecasting at the portfolio level, addressing dependency modeling limitations.

Findings

Portfolio is robust to American market downturns.

No similar robustness observed with European market stress.

Method effectively captures complex dependencies in risk estimation.

Abstract

Accurately estimating risk measures for financial portfolios is critical for both financial institutions and regulators. However, many existing models operate at the aggregate portfolio level and thus fail to capture the complex cross-dependencies between portfolio components. To address this, a new approach is presented that uses vine copulas in combination with univariate ARMA-GARCH models for marginal modelling to compute conditional portfolio-level risk measure estimates by simulating portfolio-level forecasts conditioned on a stress factor. A quantile-based approach is then presented to observe the behaviour of risk measures given a particular state of the conditioning asset(s). In a case study of Spanish equities with different stress factors, the results show that the portfolio is quite robust to a sharp downturn in the American market. At the same time, there is no evidence of this behaviour with respect to the European market.