Hybridizing Wavelet and Multiple Linear Regression Model for Crude Oil Price Forecasting

Abstract

Crude oil prices play a significant role in the global economy and contribute an important factor affecting government's plans and commercial sectors. In this paper, the accuracy of the simple wavelet multiple linear regression (WMLR) model in crude oil prices forecasting was investigated. The WMLR model was improved by combining two methods: discrete wavelet transform (DWT) and a multiple linear regression (MLR) model. To assess the effectiveness of this model, daily crude oil market-West Texas Intermediate (WTI) was used as the case study. Time series prediction capability performance of the WMLR model is compared with the Artificial neural network (ANN), autocorrelation integrated moving average (ARIMA), MLR and Generalized Autoregressive Conditional Heteroscedasticity (GARCH) models using various statistics measures. The results show that the hybrid WMLR is more accurate and perform better than of any individual model in the prediction of crude oil prices series.