A study of hybrid genetic-fuzzy models for IPO stock selection

In this paper, we present a study of hybrid genetic-fuzzy models for effective IPO stock selection. This class of models employs a stock scoring mechanism using IPO fundamental variables and applies fuzzy membership functions to re-scale the scores properly. The scores are then used to obtain the relative rankings of IPO´s and top-ranked IPO´s can be selected to form a portfolio. On top of the stock scoring model, a genetic algorithm is used for optimization of model parameters and feature selection for input variables simultaneously. We will show that the investment returns provided by our methodology significantly outperform the benchmark. Based upon the promising results obtained, we expect that this hybrid genetic-fuzzy methodology can advance the research in machine learning for finance and provide an effective solution to stock selection for IPO´s in practice.