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

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.