ATA öngörü yönteminin ampirik özelliklerinin incelenmesi

Forecasting is important in all scientific fields such as industrial, commercial, medical and economic. There are many forecasting methods in the literature, but exponential smoothing is a very popular method due to its simplicity and accuracy. Simple exponential smoothing is used for data sets randomly distributed around a constant level. Holt's linear trend method is a method that helps to deal with linearly trended data. Despite the fact that exponential smoothing methods are widely used and have been in the literature for a long time, they have some problems that potentially affect the predictive accuracy of models. Ata is a new forecasting method that has been proposed to overcome these problems and to provide better forecasts. In this thesis, the forecasting accuracy of Ata and exponential smoothing will be compared for data sets with no or linear trend. The results given in this study are obtained using simulated data sets with different sample sizes and variances and the forecast accuracy is compared using the mean squared forecast error. In line with these results, the forecast accuracy is calculated for both short and long term forecasting horizons. The results reveal that the proposed approach outperforms exponential smoothing for most types of time series data for both short and long term forecasting horizons.