Uncertain random portfolio optimization model with tail value-at-risk

In this paper, we consider a hybrid portfolio optimization problem with mature securities and newly listed securities. We employ uncertain random variables to characterize the returns of securities, and introduce tail value-at-risk (TVaR) to measure the corresponding risk. We first prove some mathematical properties of TVaR of uncertain random variables and give a numerical algorithm to approximate the TVaR. Then, we formulate several mean-TVaR models for the hybrid portfolio optimization problem and give the crisp equivalent forms of these models. Finally, we conduct a numerical example to illustrate the application of the proposed method.