Robust CVaR-based portfolio optimization under a genal affine data perturbation uncertainty set

Under a genal affine data perturbation uncertainty set, we propose a computationally tractable robust optimization method for minimizing the CVaR of a portfolio. Using L-1 norm, the robust counterpart problem can be a linear programming problem. Moreover, it is less conservative than the Quaranta and Zaffaroni's method which is under box uncertainty set. We present some numerical experiments with real market data to illustrate the behavior of robust optimization model.