Forecasting Crude Oil Price Using Kalman Filter Based on the Reconstruction of Modes of Decomposition Ensemble Model

Wei Gao,Muhammad Aamir,Adnan Aslam,Raimi Dewan,Ani Bin Shabri

doi:10.1109/access.2019.2946992

Abstract

The modes' reconstruction into the stochastic and deterministic components is proposed for forecasting the crude oil prices with the concept of “divide and conquer” and modes reconstruction. It is to reduce the complexity in the computation and to enhance the forecasting accuracy of the decomposition ensemble technique. Under the framework of “divide and conquer”, the decomposition and ensemble methodologies of forecasting power successfully improves with the proposed model based on the modes' reconstruction. The corresponding reconstruction is using average mutual information (AMI). The proposed procedure is based on four layers i.e., complex data decomposition, reconstruction of modes into components, the prediction of each individual component and assembling the final prediction. In the proposed procedure, the modes of the stochastic component are analyzed thoroughly as it influences the prediction results significantly. For verification and illustration purposes, the case study of Brent and West Texas Intermediate (WTI) daily crude oil prices data are used, and the empirical study confirms that the outcomes outperform all the considered benchmark models, including auto-regressive integrated moving average (ARIMA) model, generalized autoregressive conditional heteroscedasticity (GARCH) model, NAIVE model, ARIMA Kalman Filter model. This outcome is achieved, with the reconstruction decomposition ensemble (RDE) model along stochastic and deterministic components. Hence, it is concluded that the proposed model achieved higher forecasting accuracy and takes less computational time with the modes' reconstruction as opposed to using all the decompose modes.

Highlights

Nowadays, the important role of crude oil price forecasting in the global energy and economic system has become an appealing issue within data analysis and forecasting
(2) On publicly accessible Brent and West Texas Intermediate (WTI) crude oil prices extensive experiments were conducted on crude oil prices, and it was shown that the proposed approach outperformed several state-of-the-art methods for forecasting crude oil prices (3) We further analyzed the characteristics of the stochastic component which needs more attention which can help in significantly improving the forecasting accuracy of the crude oil prices
The experimental results indicated that all approaches; auto-regressive integrated moving average (ARIMA), generalized autoregressive conditional heteroscedasticity (GARCH), NAÏVE, ARIMAKF, ensemble empirical mode decomposition (EEMD)-ARIMA, EEMD-ARIMA-Kalman Filter (KF), EEMD(S+D)ARIMA, EEMD(S+D)-ARIMA-KF, EEMD(SD)-ARIMA and EEMD(SD)-ARIMA-KF were effective

Summary

Introduction

The important role of crude oil price forecasting in the global energy and economic system has become an appealing issue within data analysis and forecasting. Crude oil prices varied greatly, like other commodities due to market factors such as demand and supply. On another side, crude oil is treated as a special energy resource, so its prices are highly influenced by some other exogenous variables, e.g. irregular or random events [2], speculation activities [3], global economic activities [4], social and political behaviours [5] There, The associate editor coordinating the review of this manuscript and approving it for publication was Halil Ersin Soken. Apart from that, computational approaches such as artificial neural networks (ANN), decomposition-ensemble techniques of wavelet decomposition, empirical mode decomposition (EMD) and ensemble empirical mode decomposition (EEMD) have been used

Objectives

Results

Conclusion