The event adjustment model provides a very flexible framework to treat promotional effects of many kinds. This section briefly notes some of them. Its purpose is to indicate some directions you may want to take with your own business data.

The examples that are given require assigning additional event types in your event variable. Each new event type provides additional ability for Forecast Pro to explain your historic data by making the event variable more complex. Keep in mind that if your event description is overly complex, the out-of-sample performance of your model may deteriorate. You must strike the right trade-off between goodness-of-fit to your historic data and model complexity. To do this will require experimentation and monitoring of actual model performance.

Example 1. A promotion in (say) September may have effects in August and October as well. Buyers may delay purchases in August, and they may be overstocked in October. You can assign the pre- and post-promotional effects as event types of their own. These events will, of course, be associated with decreases in sales.

Example 2. Sometimes one SKU of a brand or product line is promoted but closely related SKUs are not. The result may be that the promoted SKU cannibalizes the sales of the other SKUs. You can treat this effect by assigning cannibalization events for these SKUs. But be cautious. Overuse of this technique will result in an overly complex model and possible deterioration of forecast performance.

This concludes the Building Event Models tutorial.