An Enhanced Approach to Optimizing the Stock Portfolio Selection based on Modified Markowitz MV Method

Abstract

This study presents an expert system for automatically predicting the future behavior of the stock market and determining an investment portfolio which maximizes the rate of return using a hybrid GRA / MV Model. The proposed system involved a moving Average Autoregressive Exogenous (ARX) prediction model, an enhanced clustering / classification method based on Huang-index function, RS theory ,Grey Relational Analysis (GRA) model, and Markowitz MV method. ARX is used to forecast the future trends of the collected data over the next quarter or half-year period. The enhanced clustering method is used to determine the optimal number of clusters per attribute. A RS classification module then is supplied to identify the stocks within the lower approximate sets. Finally, the selected stocks are using a hybrid GRA / MV scheme in order to maximize the rate of return of the stock portfolio. The validity and effectiveness of the clustering / classification method based on Huang-index function is first evaluated prior to that of the expert system. After that, the validity of the proposed expert system is demonstrated using electronic stock data extracted from the financial database maintained by the Taiwan Economic Journal (TEJ).