You can export a single catalog or all the catalogs from the Blueshift Platform. You can then use this data to compare the product recommendations sent to a user (available in the Campaign activity report) with the catalog information and get visibility into which products are being recommended by the Blueshift recommendation algorithms.

Export catalogs

You can export a single catalog by clicking Export in the actions menu for the catalog. The catalog is exported in CSV format and the filename is <catalog name>_<date>.csv. Once the file is ready for download, you will receive an email notification with a link to download the compressed file that contains the catalog CSV file.

To export all the catalogs, click download_icon.png. The data for all the catalogs is included in the CSV file and the filename is export_catalog_<date>.csv.

catalog_export.png

Catalog CSV file 

The exported catalog CSV file contains the following information.

Attribute Description
product_id Unique identifier of item which is unique across all your catalogs.
product_uuid The UUID for the product.
title Title of the item.
web_link URL for item on your website (http or https).
image Image Link (http or https).
start_date Indicates active/inactive status and is in ISO 8601 format. This is used to determine product recency, like recommending new arrivals.
end_date Indicates active/inactive status and is in ISO 8601 format. If present, this field indicates the date at which this product will no longer be available.
availability Indicates item status. Used for excluding out of stock products in recommendations. Also used for computing back in stock alerts when a product goes out of stock and comes back in stock.
created_at The date on which the item was added to the catalog on Blueshift.
parent_sku Ties all variants or child items together. You can use parent SKU to ensure you recommend only one variant in your recommendations. For example, only one color of the same dress, instead of multiple colors.
category Logical grouping of items. The grouping can be hierarchical with any number of levels. This is a very important field and many of the recommendation schemes use this grouping to compute trending and popular products.
tags An array of strings denoting grouping of similar products into collections or groups. The array can be used for recommending similar items based on text similarity.
extended_attributes Other attributes added for the product for segmentation and content personalization.

 

Was this article helpful?
0 out of 0 found this helpful

Comments

0 comments

Please sign in to leave a comment.