Modeling uncertainty in financial tail risk: A forecast combination and weighted quantile approach

A novel forecast combination and weighted quantile-based tail risk forecasting framework is proposed, aiming to reduce the impact of modeling uncertainty. The proposed approach based on a two-step estimation procedure. first step involves value-at-risk (VaR) forecasts at grid quantile levels. range parametric semiparametric models selected as model universe in weights are estimated by optimizing loss. In second step, expected shortfall (ES) computed average combined quantiles. quantiles weighting structure for ES determined minimizing strictly consistent joint VaR loss function Fissler–Ziegel class. applied six stock market indices its performance compared each individual universe, simple approach. results support framework.