Setting up rule-based recommendation

📖 In this guide, we will walk you through the process of setting up Rule-based Boost AI Search & Discovery Recommendation widgets to enhance your storefront's appeal and functionality.

On this page

⚠ This feature only works with Boost AI Search & Discovery V3. To find out which version of our app you are using, please follow this article.

Understanding rule-based recommendation

Rule-based recommendation are generated by the rules set up by your store. The recommended products will base on product attributes such as collection, vendor, tag, metafield, product type.

There are 2 recommendation types that can use rule-based recommendation Frequently bought together and Related items.

Set up rule-based recommendation

As a basic flow to set up a recommendation widget, to create an rule-based widget in the app’s dashboard:

  1. Go to Recommendation Recommendation widgets.
  2. Click Add new widget.
  3. On the Recommendation Type section, select Product page or Cart page > select Frequently bought together or Related items > click Next.

⚠ Currently, Rule-based recommendation is only available for Frequently Bought Together and Related items recommendation type.

  1. On Recommended product settings, select Rule-based recommendation.

  1. Toggle the desired rules to display recommended products. The recommended products will have the same attribute(s) as the source product.
    • Same collection (once enabled, you can select which collection to ignore)
    • Same product category
    • Same product type
    • Same vendor
    • Same tags (once enabled, you can select which tags to ignore)
    • Same product metafield value 1-3

You can also rearrange the rules list by simple drag-and-drop method:

⚠ The maximum number of rules that can be enabled at the same time is 4.

💡 When multiple rules are enabled, it will apply logic AND. The more rules a recommended product matches to the source product, the higher ranking it is.

To change the rule priority, you can drag and drop the selected rules. The highest rule will be considered to show the products matching this rule in the first position on the storefront.

  • Example:

You are enable two rules: same collection (1st) and same vendor (2nd)

→ All products that match the same collection and same vendor will be considered as recommended products.

    • Products in the same collection as the source product will appear first in the recommended products list.
    • After that, products from the same vendor as the source product will be displayed.

We have ignored fields so that you can exclude specific collections, tags, and metafields from the model. The input data for the model will not include these ignored values.

  • Example:

Source product has 3 tags A, B, C. Then you ignore tag B ⇒ Model will understand that the source product only has tag A, C → it will recommend the products that have the same tag A and C as the source product.

  1. Click Next.
  2. Start customizing your recommendation widgets.

Tutorial Video

Watch our tutorial video to learn how to set up Product Recommendation Widget:

If you have any questions or need further assistance, please do not hesitate to reach out to our dedicated support team at