A fuzzy rule based expert system for stock evaluation and portfolio construction: An application to Istanbul Stock Exchange

The aim of this study is to construct an appropriate portfolio by taking investor?s preferences and risk profile into account in a realistic, flexible and practical manner. In this concern, a fuzzy rule based expert system is developed to support portfolio managers in their middle term investment decisions. The proposed expert system consists of three stages. In the first stage, the stocks that are not preferred by investors are eliminated according to some fundamental thresholds and specific preferences of investor. In the second stage, the stocks are evaluated and rated by using a fuzzy rule base. In the last stage, a portfolio that is appropriate to the investor?s risk profile and preferences is constructed by using the stock ratings.The proposed expert system is validated for the period between 2002 and 2010, by using the data of 61 stocks that are publicly traded in Istanbul Stock Exchange National-100 Index and are never left out of Istanbul Stock Exchange during the validation period. The performance of the proposed system is analyzed in comparison with the benchmark index, Istanbul Stock Exchange National-30 Index, in terms of different risk profiles and investment period lengths. In most cases, the performance of the proposed expert system is superior relative to the benchmark index. However, the performance is inferior in a few periods in which unpredictable macroeconomic or political events occur. Additionally, in parallel to our expectations, the performance of the expert system is relatively higher in case of risk-averse investor profile and middle term investment period than the performance observed in the other cases.