1. PlanIQ
  2. Prepare your data
  3. Create source modules for your data collection setup

The source modules hold historical and related data, and attributes that you use to set up a data collection. 

Your feedback is important to us. To ensure you have a good content experience, we'd appreciate if you could tell us how you find the guidance on this page and if it addresses your questions. 

To take part, complete the quick survey at the end of the article, and tell us how we can improve. 

Ensure you're in the new modeling experience and you're familiar with how to build a model in Anaplan. 

Your forecast requires historical data to base the predictions on. We advise that you build a module that contains a time dimension and the essential data that you need predictions for. Then, you can export the module to PlanIQ with an export action.

If you want to include a related data set to influence your forecasts, we recommend you create a module in your source model to hold the related data. Related data can enhance the accuracy of your forecasts. 
Examples of related data are forward or historical looking marketing promotions. 

Include a time dimension and a list of IDs for historical and related data sets.

You can also add a module for attributes. Attributes group items by their shared characteristics. For example size, color. This is particularly useful for forecasts based on neural network algorithms, as they improve the results of forecasts where some items are new. 

Historical data is mandatory for PlanIQ forecasts. Related data and attributes are both optional.
Historical data is sometimes called actuals or historical actuals. 

Create a module for historical data

To create the historical data module:

  1. Create a new module and import a time dimension and a list of IDs as rows.
    For the ID list, you can use an existing list of SKUs or items. 
  2. Create a new line item as a column.
Set the dimensions so the line items are columns and time and item_id are rows.
  1. In Blueprint, format the line item as a number.
    The line item is for the numerical historical data which the forecast uses to base the predictions on.
    For example, your historical sales.
  2. Import data into the module and check that the fields map correctly.
    Ensure your module only has one column for line items, and a row for time dimension, ID list, and the numerical data.
  3. We recommend you create a view with the three columns.
    You can run the export action from this view, even if you make changes to the module.
This is how the items display.
  1. Configure an export action.
    Ensure the export CSV file has column headers to represent each line item in the module.
    For example: timestamps, IDs, and target values.

Configure an export action

To configure an export action:

  1. Select Export>Layout.
  2. For Export Format, select the comma separated values (.csv) file type.
  3. Deselect Omit summary items.
  4. Under Labels, select Include row headers.
  5. Select Save export definition.
  6. Click Run export.

Create a module for related data

To create the related data module:

  1. Create a new module and import a time dimension and a list of IDs as rows.
  2. Create some line items and position the line items on columns.
    You can create a maximum of 13 line items.
    For example: Price, Promotion, Out of stock.
The pivot for related data is similar to historical data.
  1. In Blueprint, format the line items as numbers.
    These are numerical data. 
  2. Import data into the module and check that the fields map correctly.
    Ensure your module has a column for timestamps, another for IDs, and one for each line item.
  3. We recommend you create a view with the relevant columns.
    You can run the export action from this view, even if you make changes to the module.
You can see a list of items for a particular time period.
  1. Configure an export action.
    Ensure the export CSV file has column headers to represent each line item in the module.

Create a module for attributes

To create the attributes module:

  1. Create a new module and import list of IDs as a row.
  2. Create some line items as columns.
    You can create a maximum of nine line items.
    For example: Product line, Category, Region.
There is no Time dimension for attributes so you just need to have the item_id in rows and the line items in columns.
  1. In Blueprint, format the line items as text.
  2. Import data into the module and check that the fields map correctly.
    Ensure your module has a column for IDs, and each line item.
  3. We recommend you create a view with the relevant columns.
    You can run the export action from this view, even if you make changes to the module.
The attributes group the items by flavor, type and size in this example.
  1. Configure an export action.
    Ensure the export CSV file has column headers to represent each line item in the module.