A new hybrid approach EMD-EXP for short-term forecasting of daily stock market time series data

Forecasting time series recently has attracted considerable attention in the field of analyzing financial time series data specifically stock market index. This considerable attention confined itself in the need of transparent change in the governmental policies whether attracting foreign investment or/and economical advancements. In this study, a hybrid methodology between Empirical Mode Decomposition with exponential smoothing method (EMD-EXP) is used to improve forecasting performances in financial time series. The strength of this EMD-EXP lies in its ability to predict non-stationary and non-linear time series without need to use any transformation method. Moreover, EMD-EXP also has relatively high accuracy and offer a new forecasting method in time series. The daily stock market time series data of 12 countries are applied to show the forecasting performance of the proposed EMD-EXP. Based on the three forecast accuracy measures, the results indicate that EMD-EXP forecasting performance is superior to seven traditional forecasting methods.