Static and dynamic models for multivariate distribution forecasts: Proper scoring rule tests of factor-quantile versus multivariate GARCH models

Many static and dynamic models exist to forecast Value-at-Risk other quantile-related metrics used in financial risk management. Industry practice favours simpler, such as historical simulation or its variants. Most academic research focuses on the GARCH family. While numerous studies examine accuracy of multivariate for forecasting metrics, there is little accurately predicting entire distribution. However, this an essential element asset pricing portfolio optimization problems having non-analytic solutions. We approach highly complex problem using various proper scoring rules evaluate forecasts eight-dimensional distributions: exchange rates, interest rates commodity futures. This way, we test performance models, namely, empirical distribution functions a new factor-quantile model with commonly asymmetric class.