Automatic Model Selection 

Use

Automatic model selection allows you to let the system determine which forecast model best fits your historic data.

SAP recommends automatic model selection if you do not know the trend of your historic data, if you cannot estimate how your data will develop, or if you do not want to specify a model.

Features

The system computes and compares the forecast results for all exponential smoothing methods. It selects the best of these models. Note that the system suggests the optimization of smoothing factors.

Note that optimization requires a great amount of calculation.  This is particularly true of the trend-seasonal model. The calculation cost also depends on the size of the search space and the precision of the step sizes you set (see Optimizing Smoothing Factors for Exponential Smoothing).

The suitability of a model is measured by Akaike’s Information Criterion (AIC). This takes into account the fitting error and the number of parameters for the model. The fitting error results from the residuals between the calculated forecast values and the observed values. The smaller the AIC, the better the model fits.