A Theory of the Risk for Empirical CVaR with Application to Portfolio Selection

When decisions are based on empirical observations, a trade-off arises between flexibility of the decision and ability to generalize new situations. In this paper, we focus that obtained by minimization Conditional Value-at-Risk (CVaR) argue in CVaR generalization can be understood ground theoretical results under very general assumptions system generates observations. The have implications topics related order structure selection various applications where risk-measure is used. A study portfolio optimization problem with real data demonstrates our results.