Create a Recommendations Dataset

You don't need to upload a full file when you create a new Recommendations dataset schema. A file that contains the required headers and at least three rows will suffice.

All the attributes required for a Recommendations dataset must appear in the file header, with the attribute name matching the exact spelling and case. See the dataset specifications in the Recommendations dataset overview to ensure success.

Follow these steps to create a Recommendations dataset.

  1. Click DATASETS in the top navigation bar, and then, if necessary, select Product Data.

    Callout of the 'CREATE DATASET' button on the All Datasets list page

  3. Click Recommendation and then click NEXT.

    Step 1 of the 'Create Dataset Schema' wizard, with Recommendation selected for the dataset type and a callout of the NEXT button

  4. Name the dataset and then click NEXT.

    The name must begin with a letter and can contain only letters, numbers, and underscores.

    Step 2 of the 'Create Dataset Schema' wizard, with a name for the dataset in the appropriate field and a callout of the NEXT button

  5. Drag and drop the file into the upload area, and then wait for the platform to validate the data.
    • If the file fails validation, an error message appears that states the problem encountered. Revise the file, click RE-UPLOAD, and then drag and drop the revised file into the upload area.

      Step 3 of the Create Dataset Schema wizard, with a validation error message that reads, 'Whoops! There was an error processing your file. Missing required fields: id' An arrow calls out the 'RE-UPLOAD' button

    • If no errors are detected, ensure the sample shown is correct and then select Looks good.

      Step 3 of the Create Dataset Schema wizard, with a message that reads, 'Your file looks good!' and a callout of 'Looks good' checkbox


    Callout of the 'CONFIRM AND CREATE' button in the Create Dataset Schema wizard

Once Monetate finishes creating the schema, the details page for the newly created Recommendations dataset loads, with the Current Updates table showing the file you just uploaded listed and the PENDING status at the top-right corner. This status appears until the platform finishes processing the dataset.

The details page for a new Recommendations dataset showing the Current Updates table and the PENDING status

With the schema created, you can now update the dataset as needed, especially if you used a file that only contained a few rows. A full update replaces the entire dataset, and a partial update allows you to add new rows or update existing ones. See Update a Recommendations Dataset for more information.

You can access the dataset's files on the Update History tab of its details page in the Monetate platform.

Monetate retains dataset files for 180 days from the date it was uploaded. Once a file is out of this retention period, it still appears on the dataset's Update History tab, but you cannot download it.