S&P 500 Index Direction Forecasting from 1976 to 2010: A Fuzzy System Approach

Abstract

Abstract. Investors are not always completely rational and they do not always work only with numbers. Sometimes, they use linguistic concepts to make their decisions. Fuzzy logic is helpful in handling such situations. This article differs from other studies in this area by applying fuzzy logic for forecasting the direction/sign of stock market indexes. The article also presents a model for forecasting the direction/sign of stock market indexes using a fuzzy system, and this model is applied in the prediction of the S&P 500 Index. The rules of the model were established between 1970 and 2009, and the test period was from 1976 to 2010. Despite the fact that the estimated model produced a linguistic output, it was possible to delineate a statistically significant investment strategy, which outperformed a buy-and-hold one. In addition, the success rate calculated was also statistically significant. Another difference from other studies is that the proposed model does not return an exact output, but a probabilistic one of linguistic variables. The proposed model, with its probabilistic output, can be used as a support for investment decisions. In other words, the linguistic output does not force the investor to blindly follow the proposed strategy.