Mean target semi-absolute deviation model for portfolio selection with uncertain returns

摘要

This paper discusses the uncertain portfolio selection problem when security returns are hard to be well reflected by historical data. The security returns are regarded as uncertain variables. A target semi-absolute deviation risk measure is introduced. Based on the concept of target semi-absolute deviation, a mean target semi-absolute deviation model is proposed. In addition, the gravitation search algorithm is introduced to solve the proposed model. Finally, a numerical example is given to illustrate the application of the proposed model.