Nonlinear Forecasting of Energy Futures
This paper proposes the use of the Brownian distance correlation for feature selection and for conducting a lead-lag analysis of energy time series. Brownian distance correlation determines relationships similar to those identified by the linear Granger causality test, and it also uncovers additional non-linear relationships among the log return of oil, coal, and natural gas. When these linear and non-linear relationships are used to forecast the direction of energy futures log return with a non-linear classification method such as support vector machine, the forecast of energy futures log return improve when compared to a forecast based only on Granger causality.
KeywordsFinancial forecasting Lead-lag relationship Non-linear correlation Energy finance Support vector machine Artificial agents
The author thanks participants of the Eastern Economics Association meeting 2014, the AAAI 2014 Fall Symposium on Energy Market Predictions, Dror Kennett, Alex Moreno, and three anonymous referees for their comments and suggestions. The author also thanks the Howe School Alliance for Technology Management for financial support provided to conduct this research. The opinions presented are the exclusive responsibility of the author.
- 2.Aruga, K., Managi, S.: Linkage among the U.S. energy futures markets. In: 34th IAEE International Conference Institutions, Efficiency and Evolving Energy Technologies. Stockholm (2011)Google Scholar
- 4.Asche, F., Gjolberg, O., Volker, T.: The relationship between crude oil spot and futures prices: Cointegration, linear and nonlinear causality. Energy Econ. 30, 2673–2685 (2008)Google Scholar
- 10.Granger, C.W.J.: Essays in Econometrics: The Collected Papers of Clive W.J. Granger. Cambridge University Press, Cambridge (2001)Google Scholar
- 12.Hartley III, P., Rosthal, K.B.M., K.E, : The relationship of natural gas to oil prices. Energy J. 29(3), 47–65 (2008)Google Scholar
- 21.Ramberg, D.J.: The relationship between crude oil and natural gas spot prices and its stability over time, master of Science thesis, Massachusetts Institute of Technology (2010)Google Scholar
- 24.US Energy Information Administration: Annual Energy Outlook. US Energy Information Administration, Washington D.C (2011)Google Scholar
- 25.US Energy Information Administration, : Annual Energy Outlook. US Energy Information Administration, Washington D.C. (2013)Google Scholar