Portfolio level (un)conditional risk measure estimation for backtesting using Vine Copula and ARMA-GARCH models.
-
Updated
Jan 22, 2024 - R
Portfolio level (un)conditional risk measure estimation for backtesting using Vine Copula and ARMA-GARCH models.
Automatic optimal sequential investment decisions. Forecasts made using advanced stochastic processes with Monte Carlo simulation. Dependency is handled with vine copulas.
MATVines: A Vine Copula Package for MATLAB. To cite this software publication: https://www.sciencedirect.com/science/article/pii/S2352711021000455
D-Vine GAM Copula based Quantile Regression
Gradient-Boosted Estimation of Generalized Linear Models for Conditional Vine Copulas
Code for the case studies and theoretical visualizations for the master thesis 'Estimation and Backtesting of the Expected Shortfall and Value at Risk using Vine Copulas'
Monte Carlo research on how unknown marginal distributions and simplifying assumptions affect copula estimation error across families and sample sizes.
This repository contains R code for conditional inference using copula models.
Neural D-vine scenarios, mixed historical/synthetic training, and scenario-CVaR recurrent TD3 for constrained portfolio control.
To associate your repository with the vine-copulas topic, visit your repo's landing page and select "manage topics."