Portfolio Selection under Parameter Uncertainty using a Predictive Distribution

Ji Jung Im

Hyun Soo Lim

and

Sung Sub Choi

We propose a portfolio selection model based on a generalized hyperbolic
predictive distribution. This distribution incorporates uncertainties in mean and volatility of market returns. We then select an optimal portfolio with expected utility calculated under the predictive distribution. We demonstrate the performance of the new approach by applying it to simulated and real market data.