Home

“The ATA Method is a new alternative forecasting method. This method is alternative to two major forecasting approaches: Exponential Smoothing and ARIMA.“

The ATA method works by modifying the smoothing constants of various exponential smoothing models in a way that the smoothing constant becomes a function of t. This modification helps deal with initialization problems and makes the optimization process easier. Also with ATA it is possible to assign past information equal weights. These new achievements help ATA stay on top of its competition.

For details please see our results on the M1 and M3 competition data sets by visiting our Software and Data and Results sections.