Sensitivity estimation of conditional value at risk using randomized quasi-Monte Carlo

Conditional value at risk (CVaR) is a popular measure for quantifying portfolio risk. Sensitivity analysis of CVaR common in management and gradient-based optimization algorithms. In this paper, we study the infinitesimal perturbation estimator sensitivity using randomized quasi-Monte Carlo (RQMC) simulation. RQMC has proved valuable financial option pricing with better rate convergence compared to Monte sampling, but theoretical guarantees new application shall be studied. To end, first prove that RQMC-based strongly consistent under very mild conditions. Under some technical conditions, yields mean error O(n?1/2?1/(4d?2)+?) arbitrarily small ?>0, where d represents dimension points n sample size. Some typical applications estimation are conducted both show how results can applied, as well provide numerical documenting superiority estimator.