Forecasting of Indonesian Crude Oil Price using EEMD- LSTM
Nuchaila Ainiyah (a*), Heri Kuswanto (a), Kartika Fithriasari (a)

(a) Department of Statistics, Institut Teknologi Sepuluh Nopember (ITS), Sukolilo, 60111, Indonesia
*nuchela24[at]gmail.com

Abstract

Crude oil is a commodity that plays a very important role in all economies. The direct impact of fluctuations in crude oil prices is changes in operational costs. The development of Indonesia^s crude oil price has recently been trending throughout early January, so this has caused the crude oil price chart to fluctuate. The instability of crude oil prices was preceded by an increase in oil prices. Ensemble empirical mode decomposition (EEMD) was employed to decompose runoff series into several stationary components and a trend. The long short-term memory (LSTM) model was used to build the prediction model for each sub-series.The model input set contained the historical flow series of the simulation station its upstream station and the historical meteorological element series. The final input of the LSTM model was selected by MI method. To verify the effect of EEMD, this study used the Radial Basis Function (RBF) model to predict the sub-series, which was decomposed by EEMD. This study aims to predict price of Indonesian crude oil using Ensemble empirical mode decomposition (EEMD) and long short-term memory (LSTM).

Keywords: Crude Oil, EEMD, LSTM

Topic: Mathematics and Statistics