Collections are a powerful tool to create groups of items based on dynamic rules. For instance, one can define the Cyber Monday collection as "the set of all items from the Electronics category which cost less than $200, as well as all laptops that cost less than $800." You can also imagine a collection composed of SKUs curated by a merchant team for a holiday email campaign

Ranking

Like search and other browse pages, ranking of products is dynamic based on user behavior and the ML algorithm's estimation of the products most likely to move your target KPIs (these are defined during onboarding in consultation with customer success and data science teams, most typically focusing on a mix of conversion and/or RPV), as well as any rules defined for browse pages.

Product membership

The products shown for a collection can be defined by one of the following methods:

• Products can be added by SKU manually with an easy CSV.
• Products can also be defined using a rich set of expressions utilizing the entire facet taxonomy.

Collections can also include a mix of products added via individual SKUs as well as via facet rules.

Update time

Products added to a collection via SKU upload take 5-10 minutes to display in a collection, while products added to a collection via dynamic facet rules will take about 2 minutes to show up in a collection.

If you switch from a collection composed only of dynamic rules to a collection composed only of individual SKU upload items, you should give the system time to rebuild the collection items before removing the dynamic conditions (you don't want the collection to be left empty).

Read more

For more detailed technical documentation, reference our feature and API documentation for collections: configuring collections.