Using Promotion Patterns Derived from Historical Data
Use this function to derive promotional uplifts from historical data, create promotion patterns based on these uplifts, and apply these patterns to future promotions.
You have created a promotion.
Linear regression is used for analysis of the historical data. You can also choose seasonal linear regression (like forecast strategy 35)
This takes you to the promotion planning desktop.
The system applies linear regression to the historical data, thus creating an ex-post forecast, and displays the results in the row Ex-post estimate. The difference between the historical data and the ex-post estimate is displayed in the Promotion pattern row. Periods where the promotion pattern amounts to more than 20% of the history are highlighted in red.