Improved EEMD-based crude oil price forecasting using LSTM networks

Abstract

Considering the actual demand of crude oil price forecasting, a novel model based on ensemble empirical mode decomposition (EEMD) and long short-term memory (LSTM) is proposed. In practical work, the model trained by historical data will be used in later data. Then the forecasting models based on EEMD need re-execute EEMD to update decomposition results of price series after getting new data. In this process, the decomposition results of same period will not stay entirely identical, and even the number of decomposition results could change Unfortunately, in this case the traditional decomposition-ensemble models trained by historical data break down. To overcome this disadvantage, a method to select same number of proper inputs in different situations of decomposition results is developed. And for extracting feature from selected components more adequately, LSTM is introduced as forecasting method to predict price movement directly. For illustration and verification purposes, the proposed model is used to predict the crude oil spot price of West Texas Intermediate (WTI). Empirical results demonstrate that the proposed model still work well when the number of decomposition results varies, thus is promising for forecasting crude oil price.