Forecasting output using oil prices: A cascaded artificial neural network approach

Abstract Recent evidence suggests that oil prices affect output of the economy in a non-linear complex fashion. However, there is no clear agreement on the unknown functional form. An application of artificial neural network for short-term forecasting of GDP using oil prices and utilizing cascaded learning is proposed. We find that the mean absolute forecasting error and the mean square forecasting error is reduced by applying cascaded neural network relative to conventional artificial neural networks and popular linear models. Results also indicate that the developed forecasting approach is useful and point to the potential of this methodology for other economic applications. Our results are important for improving economic forecasts and introduce oil prices as a strong candidate for future forecasting exercises.

[1]  J. Burbidge,et al.  Testing for the Effects of Oil-Price Rises using Vector Autoregressions , 1984 .

[2]  S. Fischer.  Rational Expectations and Economic Policy , 1980 .

[3]  M. Gisser,et al.  Crude Oil and the Macroeconomy: Tests of Some Popular Notions: A Note. , 1986 .

[4]  Steven J. Davis,et al.  Regional Labor Fluctuations: Oil Shocks, Military Spending, and Other Driving Forces , 1997 .

[5]  James D. Hamilton.  A Parametric Approach to Flexible Nonlinear Inference , 2001 .

[6]  Steven J. Davis,et al.  Sectoral Job Creation and Destruction Responses to Oil Price Changes , 1999 .

[7]  Halbert White,et al.  Artificial neural networks: an econometric perspective ∗ , 1994 .

[8]  M. Hooker,et al.  What happened to the oil price-macroeconomy relationship? , 1996 .

[9]  Andrew J. Oswald,et al.  Unemployment Equilibria and Input Prices: Theory and Evidence from the United States , 1998, Review of Economics and Statistics.

[10]  J. D. Schaffer,et al.  Combinations of genetic algorithms and neural networks: a survey of the state of the art , 1992, [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks.

[11]  C. Chatfield,et al.  Neural networks: Forecasting breakthrough or passing fad? , 1993 .

[12]  Esfandiar Maasoumi,et al.  Artificial neural networks for some macroeconomic series: A first report , 1994 .

[13]  M. Hooker.  This is what happened to the oil price-macroeconomy relationship: Reply , 1996 .

[14]  Richard Schmalensee,et al.  Advertising and aggregate consumption: an analysis of causality , 1980 .

[15]  Frederic S. Mishkin,et al.  Predicting U.S. Recessions: Financial Variables as Leading Indicators , 1995, Review of Economics and Statistics.

[16]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[17]  Benjamin M. Friedman,et al.  Money, Income, Prices, and Interest Rates , 1992 .

[18]  James D. Hamilton.  What is an Oil Shock? , 2000 .

[19]  James D. Hamilton.  This is what happened to the oil price-macroeconomy relationship , 1996 .

[20]  Robert W. Rich,et al.  Oil and the Macroeconomy: A Markov State-Switching Approach , 1997 .

[21]  Kiseok Lee,et al.  Oil Shocks and the Macroeconomy: The Role of Price Variability* , 1995 .

[22]  John C. B. Cooper.  Artificial neural networks versus multivariate statistics: An application from economics , 1999 .

[23]  E. Prasad.  The Employment and Wage Effects of Oil Price Changes: A Sectoral Analysis , 1995, SSRN Electronic Journal.

[24]  C. Nelson,et al.  Trends and random walks in macroeconmic time series: Some evidence and implications , 1982 .

[25]  Greg Tkacz.  Neural network forecasting of Canadian GDP growth , 2001 .

[26]  Knut Anton Mork,et al.  Oil and the Macroeconomy When Prices Go Up and Down: An Extension of Hamilton's Results , 1989, Journal of Political Economy.

[27]  J. L. Pierce,et al.  The Effects of External Inflationary Shocks , 1974 .

[28]  Prakash Loungani.  Oil Price Shocks and the Dispersion Hypothesis , 1986 .

[29]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[30]  Kiseok Lee,et al.  On the Dynamic Effects of Oil Price Shocks , 2002 .

[31]  R. Pindyck.  Energy Price Increases and Macroeconomic Policy , 1980 .

[32]  Norman R. Swanson,et al.  A Model Selection Approach to Real-Time Macroeconomic Forecasting Using Linear Models and Artificial Neural Networks , 1997, Review of Economics and Statistics.

[33]  Jacques de Villiers,et al.  Backpropagation neural nets with one and two hidden layers , 1993, IEEE Trans. Neural Networks.

[34]  F. Diebold,et al.  Comparing Predictive Accuracy , 1994, Business Cycles.

[35]  Arturo Estrella,et al.  The term structure as a predictor of real economic activity , 1991 .

[36]  International interdependence of national growth rates: A structural trends anakysis , 1997 .

[37]  James D. Hamilton,et al.  A Reexamination of the Predictability of Economic Activity Using the Yield Spread , 2000 .

[38]  R. Solow.  What to Do (Macroeconomically) When OPEC Comes , 1980 .

[39]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[40]  Magdi S. Mahmoud,et al.  Cascaded artificial neural networks for short-term load forecasting , 1997 .