Can Neural Networks Applied to Time Series Forecasting Learn Seasonal Patterns: an Empirical Investigation

Artificial neural network are increasingly being applied to time series forecasting, but with mixed results. There appears to be as many methods as there are studies. This research investigates whetkr prior statistical deseasonalising of data is necessary for producing accurate forecasts with neural networks, or whether the network can adequately model seasonality. Neural network trained with deseasonalised &a from [5] were conquared with neural networh devcbped without prior deseasonalisatwn. Both sets of neural networks produced forecasts for the 68 monthly time series fiom the M-competition 171. Results indicate that neural network forecasts fiom deseasonalised data we significantly more accurate than the forecasts produced by neural networks which modelled seasonality.