Forecasting Crude Oil Prices with the Google Index. (May 2017)

• Record Type: Journal Article
• Authors: Yao, Ting; Zhang, Yue-Jun
• Is Part Of: Energy procedia. Volume 105(2017)
• Page Start: 3772
• Page End: 3776
• Publication Date: 2017-05
• Subjects: WTI crude oil -- Forecast -- Google Index -- ARIMA -- ARMA-GARCH; Power resources -- Congresses; Power resources -- Periodicals; Power resources; Conference proceedings; Periodicals; 333.7905
• DOI: 10.1016/j.egypro.2017.03.880
• Languages: English
• ISSNs: 1876-6102

Abstract

Abstract: As crude oil price volatility is susceptible to oil-related events and the Internet search data can effectively reflect the psychological behaviours of investors in crude oil market. In this sense, we explore the effect and predictive power of the Google Index on crude oil prices by incorporating the Google Index as an exogenous variable into the ARIMA (Auto-regressive Integrated Moving Average) and ARMA-GARCH (Auto-regressive Moving Average-Generalized Auto-Regressive Conditional Heteroscedasticity) models. The empirical results indicate that there exists a negative effect of the Google Index on crude oil prices, but the Google Index cannot help to forecast crude oil prices.