ABSTRACT
In this chapter we propose the application of argumentation and hybrid evolutionary multi-model partitioning algorithms for developing the PORTRAIT (PORTfolio constRuction based on ArgumentatIon Technology) tool. This hybrid computational intelligence approach comprises the integration of an argumentation-based decision-making framework and a hybrid evolutionary forecasting algorithm, which combines evolutionary algorithms (EAs), Lainiotis’ multi-model partitioning (MMP) theory and extended Kalman filters (EKF). The argumentation framework is employed in order to develop mutual funds performance models and to select a set of mutual funds, which will compose the final portfolio, taking into account the investor preferences and the market context. The hybrid evolutionary forecasting algorithm is applied in order to forecast the market status (inflating or deflating) for the next investment period. The proposed methodology gives the opportunity to a decision maker (fund manager) to construct multi-portfolios of mutual funds that perform better than the average mutual fund and achieve higher returns than the Athens Stock Exchange General Index for medium- to long-term investments. The knowledge engineering approach and the PORTRAIT tool development steps and architecture are also presented and discussed.
