The ESM Procedure

All the parameters (smoothing weights) associated with the exponential smoothing model used to forecast the time series (as specified by the MODEL= option) are optimized based on the data, with the default parameter restrictions imposed. If the TRANSFORM= option is specified, the transformed time series data are used to estimate the model parameters.

The techniques used in the ESM procedure are identical to those used for exponential smoothing models in the Time Series Forecasting System of SAS/ETS software. See Chapter 45: Overview of the Time Series Forecasting System, for more information.