Forecasting Tala-AUD using time series and artificial neural network model

The paper compares the autoregressive time series Artificial Neural Network model, exponential smoothing with trend, and Winters Method model to forecast exchange rate of Samoan Tala/AUD during the period of January 3 2008 to September 28 2012. We use daily exchange rate data to do our study. The performance of the models was measured by using varies error functions such as Root Square mean error (RSME), Mean absolute error (MAE), and Mean absolute percentage error (MAPE). The empirical findings suggest that ANN model is an effective tool to forecast the Tala/AUD.