Forecast Performance of Neural Networks and Business Cycle Asymmetries

We investigate forecast performance of artificial neural network models using Ashley, et al. (1980) and employ neural network nonlinearity test proposed by Lee, et al. (1993) to find possible existence of business cycle asymmetries in Canada, France, Japan, UK, and USA real GDP growth rates. Our results show that neural network models are more accurate than linear models for in-sample forecasts. However, when comparing the out-of-sample, linear models performed better than neural network models in all series. Results from neural network tests show that business cycle asymmetries do prevail in all the series