Skip to main content
Product recommendations are a tool that automatically matches relevant products to different situations. You can use them to build personalized collections for returning customers, surface bestsellers for new visitors, or display complementary products next to a specific item on your website.

​
Where you can use recommendations

You can deploy recommendations in three primary contexts:
  • Email campaigns and newsletters — embed personalized product blocks in any email.
  • Recommendation widgets on your website — show dynamic product collections directly on storefront pages.
  • API operations — pull recommendation output through the API for further processing in any channel.

​
How to create a recommendation algorithm

Setting up a new algorithm takes four steps:
1

Open the recommendations section

In Maestra, go to Content → Product Recommendations.
2

Select an algorithm

Choose the algorithm type that matches your objective (bestsellers, similar products, related products, and so on).
3

Configure the settings

Fill in the settings specific to the algorithm type you selected.
4

Launch and wait for recalculation

Save the algorithm and wait for its first recalculation to finish.
Algorithms are not available for selection in campaigns or widgets until their initial recalculation finishes. Algorithms left in draft status also remain unavailable.

​
How recommendations work in multi-brand projects

In multi-brand environments, recommendation algorithms are available across all brands. However, when recommendations are generated for a campaign, only products from the brand where the mechanic was created are taken into account. Cross-brand recommendations are not allowed. The brand used for recommendation output depends on the channel:
ContextHow the brand is determined
Email campaignsUses the brand selected in the campaign
Website recommendation widgetsDetermined by the integration endpoint’s brand settings
API operationsUses the brand configured on the integration point

​
How regional data is handled

When regional data is present in your catalog, the system uses a two-phase approach:
  1. During recalculation — regional availability and pricing are considered. All other regional attributes fall back to the master feed values.
  2. At output time — regional product data matching the customer’s zone is substituted into the final recommendation.
This means a customer in one region can see prices and stock relevant to their location, while the underlying algorithm still operates on a consistent catalog.

​
Product grouping

Product groups bundle items together by shared characteristics such as color or size. Recommendation algorithms automatically account for these groups to prevent duplicate product suggestions. During calculation, grouped products are treated as a single unit and their interactions are summed. At output, the algorithm displays the most popular product from that group, so customers never see two near-identical items side by side.

​
Real-time algorithms

Some algorithms update dynamically within seconds based on customer behavior on your site. These include:
  • Related products
  • Similar products
  • Bestsellers in viewed categories
Real-time algorithms are not recommended for trigger-based campaigns. Because they react instantly to customer behavior, they can return empty or irrelevant results at the moment a trigger fires.

​
Available algorithm types

Maestra offers several algorithm types. Pick the one that fits the moment in the customer journey you want to influence.
Suggests products comparable to those the customer viewed in the current session. Updates in real time as they browse.
Displays items comparable to those in a specific collection. Updates when new products are added or removed from the list.
Lets you manually select product categories that are relevant to a customer’s previous purchase. Updates when orders are modified.

​
Configuration options

Settings vary depending on the algorithm type you select, but common options across algorithms include:
  • Scheduled product segments — restrict the algorithm to a specific segment of your catalog.
  • Product grouping — automatically applied to remove duplicates from the output.
  • Regional data — controls availability and pricing during calculation.
  • Brand selection — varies by implementation across emails, widgets, and API operations.
Once your algorithm has finished its first recalculation, it becomes available for selection inside campaigns, widgets, and API calls — ready to deliver personalized product picks across every channel.