Forecasting the Thailand stock market using evolution strategies

This paper proposes a new prediction function for the Stock Exchange of Thailand (SET index). Included in the proposed prediction function are the important economic factors: namely, the Dow Jones, Nikkei, and Hang Seng indexes; the minimum loan rate (MLR); and the previous SET index. The tuning coefficients of each factor in this research were calculated using the two-membered evolution strategy (ES) technique. The experiment was conducted by analysing the SET index during three different time periods. The first time period extended from January 2004 to December 2004, and the second time period extended from 9 August 2005 to December 2005. These data were used to evaluate the performance of the proposed prediction function for short-term periods by comparing the results with those achieved using the existing methods. Lastly, the long-term period data extending from January 2005 to March 2009, which covered 1040 days in totals, were used to predict the SET index. The results show that the proposed prediction function not only yields the lowest mean absolute percentage error (MAPE) for short-term periods but also yields a MAPE lower than 1% for long-term periods.