When you create a recommendation, you create a recommendation unit that contains the recommended product items.
When you activate the recommendation unit, Adobe Commerce starts to collect data to measure impressions, views, clicks, and so on. The Product Recommendations table displays the metrics for each recommendation unit to help you make informed business decisions.
On the Admin sidebar, go to Marketing > Promotions > Product Recommendations to display the Product Recommendations workspace.
Specify the Store View where you want the recommendations to display.
Page Builder recommendation units must be created in the default store view, but then can be used anywhere. To learn more about creating product recommendations with Page Builder, see Add Content - Product Recommendations.
Click Create Recommendation.
In the Name your Recommendation section, enter a descriptive name for internal reference, such as
Home page most popular.
In the Select page type section, select the page where you want the recommendation to appear from the following options:
You can create up to five active recommendation units for each page type, and up to 25 for Page Builder. The page type is grayed out When the limit is reached.
Recommendation name and page placement
In the Storefront display label section, enter the label that is visible to your shoppers, such as “Top sellers”.
In the Choose number of products section, use the slider to specify how many products you want to appear in the recommendation unit.
The default is
5, with a maximum of
In the Select placement section, specify the location where the recommendation unit is to appear on the page.
(Optional) To change the order of the recommendations, select, and move the rows in the Choose position table.
The Choose position section displays all recommendations (if any) created for the page type you selected.
Recommendation order on page
(Optional) In the Filters section, apply filters to control which products appear in the recommendation unit.
Recommendation product filters
When complete, click one of the following:
Save as draft to edit the recommendation unit later. You cannot modify the page type or recommendation type for a recommendation unit in a draft state.
Activate to enable the recommendation unit on your storefront.
Some recommendation types use behavioral data from your shoppers to train machine learning models to build personalized recommendations.
Requires only catalog data. No behavioral data is needed for these:
Based on last six months of storefront behavioral data:
Popularity-based recommendation types use the last seven days of storefront behavioral data:
Readiness indicator values are expected to fluctuate due to factors such as the overall size of the catalog, volume of product interaction events (views, adds to cart, purchases), and percentage of skus that register those events within a certain time window, as listed above. For example, during peak holiday season traffic, the readiness indicators might show higher values than in times of normal volume.
To help you visualize the training progress of each recommendation type, the Select Recommendation type section displays a measure of readiness for each type. These readiness indicators are calculated based on a couple factors:
Sufficient result set size: Are there enough results being returned in most scenarios to avoid using backup recommendations?
Sufficient result set variety: Do the products being returned represent a variety of products from your catalog? The goal with this factor is to avoid having a minority of products being the only items recommended across the site.
Based on the above factors, a readiness value is calculated and displayed. A recommendation type is considered ready to deploy when its readiness value is 75% or higher. A recommendation type is considered partially ready when its readiness is at least 50%. A recommendation type is considered not ready to deploy when its readiness value is less than 50%. These are general guidelines but each individual case can differ based on the nature of collected data as outlined above.
Indicators may never reach 100%.
The Recommended products preview panel is always available with a sample selection of products that might appear in the recommendation unit when it is deployed to the storefront.
To test a recommendation when working in a non-production environment, you can fetch recommendation data from a different source. This allows merchants to experiment with rules and preview the recommendations before deploying to production.
|Name||The name of the product.|
|SKU||The Stock Keeping Unit assigned to the product|
|Price||The price of the product.|
|Result Type||Primary - indicates that there is enough training data collected to display a recommendation.
Backup - indicates that there is not enough training data collected so a backup recommendation is used to fill the slot. Go to Behavioral Data to learn more about machine learning models and backup recommendations.
As you create your recommendation unit, experiment with the page type, recommendation type, and filters to get immediate real-time feedback about the products that will be included. As you begin to understand which products appear, you can configure the recommendation unit to meet your business needs.
Adobe Commerce filters recommendations to avoid displaying duplicate products when multiple recommendation units are deployed on a single page. As a result, the products that appear in the preview panel might differ from those that appear in the storefront.
You cannot preview the
Recently viewed recommendation type because the data is not available in the Admin.