Comparison of Stock Selection Methods: An Empirical Research On The Borsa Istanbul

This paper compares the performances of stock selection methods developed by artificial neural network (ANN), second order stochastic dominance (SSD), and Markowitz portfolio optimization generating annual portfolios whose stocks are selected from several types indexes traded in Borsa Istanbul. Daily returns SSD Markowitz, ratios ANN models, taken as inputs, with following outputs. By perspective literature, this study carries unique value for including comparisons these purpose higher returns. Thus, two questions emerge: "Are able to overcome losses during financial crises bear or bull periods, can they provide positive alpha?" Results indicate that average generated relatively than but all three models alpha over indexes. However, none could negative economic crises.