Preparing Attributes for Your Project

An important consideration for many forecasting projects involves selecting variables from the data source to be used as attributes. Attributes are used to create filtersa set of specified criteria that are applied to data in order to identify the subset of data for a subsequent operation, such as continued processing. . Use these filters to query the time seriesan aggregation of transactional data into specified time intervals and sorted according to unique combinations of the default attributes (BY variables) based on selected values for one or more attributes. For more information about filters, see Working with Filters.

Variables in the input data set for a project can be assigned as BY variables. BY variables are the default attributes for the project. Data from the dependent variable is aggregated based on the unique values of the BY variables assigned to the project.

If you want to add more variables as attributes, you can import them from an external data source. As you are preparing your data for forecasting projects, determine which variables should be included in the input data set as default attributes, and which variables you want to import as additional attributes.

The following guidelines are required for the external data source for the attributes.

• The data source with the additional attributes must include the same variable names as the existing BY variables in the original data source for the project. For example, if the original BY variables in the time series project are Location and Category, then the attribute table must include columns for Location and Category.
• The imported attributes must contain a row for each unique combination of the default attributes (BY variables) as defined in the input time series or external forecasta numerical prediction of a future value for a specified time period for each unique combination of BY variable values table. For example, assume the data source for the project has observations with this combination of default attributes:
  • Location = Miami
  • Category = Shoes

  The imported attributes table must have exactly one row with this same combination. When the table is imported, it is checked to verify that all of the unique values for the default attributes match.

If you intend to use segmentation in your project, see Defining Project Segments for additional considerations for the attributes data set.

See Also

• Working with Attributes