Hybridizing Wavelet and Multiple Linear Regression Model for Crude Oil Price Forecasting
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 p
- PDF / 332,849 Bytes
- 8 Pages / 439.37 x 666.142 pts Page_size
- 46 Downloads / 232 Views
Hybridizing Wavelet and Multiple Linear Regression Model for Crude Oil Price Forecasting Ani Shabri and Ruhaidah Samsudin
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.
Keywords Wavelet Multiple linear regression Forecasting
16.1
GARCH, ARIMA Crude oil
Introduction
The international crude oil prices play an important part in the economy as the trends in changing oil prices will affect the financial markets. Crude oil prices do play a significant role in the global economy and constitute an important factor A. Shabri (&) Department of Science Mathematic, Faculty of Science, Universiti Teknologi Malaysia, Johor Bahru, Malaysia e-mail: [email protected] R. Samsudin Department of Software Engineering, Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, Malaysia e-mail: [email protected] © Springer Nature Singapore Pte Ltd. 2017 A.-R. Ahmad et al. (eds.), Proceedings of the International Conference on Computing, Mathematics and Statistics (iCMS 2015), DOI 10.1007/978-981-10-2772-7_16
157
158
A. Shabri and R. Samsudin
affecting government’s plans and commercial sectors. Therefore, proactive knowledge of its future fluctuations can lead to better decisions in several managerial levels. Due to the importance of crude oil price in future, there have been abundant studies on analysis and forecasting of crude oil price. Crude oil price forecasting has been a challenging topic in the field of energy market research. The application of classical time series models such as Autoregressive Moving Average (ARMA) [1, 2] and Generalized Autoregressive Conditional Heteroscedasticity (GARCH) type models [3–5] for crude oil forecasting has received much attention in the last decade. However, they are basically linear models and have a limited ability to capture non-linearities and nonstationary in crude oil forecasting. In 2014, wavelet transforms has become a useful method for analyzing variations, periodicities and trends in time series. Recently, new hybrid models on wavelet transform processes have been improved for forecasting. For example the wavelet-neural network [6–8], wavelet-least
Data Loading...
