Data Requirements (Optimization - Forecast)

A Forecast model needs a transactions source to run. It can be either a Data Source or a Datamart.

The source should contain a minimum of 2 years of transaction history, with the following columns:

Field	Required?	Comment

Field	Required?	Comment
Date	Yes	Should be defined as a dimension in DS/DM
Product	Yes	Typically Product ID.
Revenue	Yes	Typically end-customer price x quantity Extended to the quantity. It is better to avoid negative or null values.
Quantity	Yes	It is better to avoid negative or null values (they are filtered out by default by the model itself). It is possible to run the model with the log of the quantity. This may produce better outputs when there are small and large quantities in the dataset (e.g. many long-tail products).
Revenue at List Price	No	Typically list price x quantity. This is used to calculate discount rate based on the revenue. It is highly recommended to include this where possible.
Store	Yes	Not used, will be removed in the next version.
Product categorical features	No	Here you may include any categorical columns related to the product that may influence sales. While not strictly required to run the model, this is key to getting proper outputs. Examples include Product Category, Competitor Name, Product Life cycle, Tag for promotions/discounts.
Product numerical features	No	Numerical features may include any numerical attributes that can be averaged over the selected time period.
Customer	Yes	Required only if the check button “Add a Customer Dimension” is checked. Otherwise, the user entry is not set.
Customer Categorical Features	No	User entry set only if the check button “Add a Customer Dimension” is checked. Any categorical columns related to the customer that may influence sales.

It is also required to set the data filter in “Filter” to get complete periods (and not e.g. half a week at the beginning or the end of the scope).