A dynamic artificial neural network model for forecasting time series events

Neural networks have shown to be an effective method for forecasting time series events. Traditional research in this area uses a network with a sequential iterative learning process based on the feed-forward, back-propagation approach. In this paper we present a dynamic neural network model for forecasting time series events that uses a different architecture than traditional models. To assess the effectiveness of this method, we forecasted a number of standard benchmarks in time series research from forecasting literature. Results show that this approach is more accurate and performs significantly better than the traditional neural network and autoregressive integrated moving average (ARIMA) models.