⚠️ This feature only works with Boost AI Search & Discovery V2 and above. To find out which version of our app you are using, please follow this article.
Understanding rule-based recommendation
Rule-based recommendations are generated by the rules set up by your store. The recommended products will be based on product attributes such as collection, vendor, tag, metafield, and product type.
Two types of recommendation widgets can use rule-based recommendations Frequently bought together and Related items.
Set up rule-based recommendation
As a basic flow to set up a recommendation widget, to create a rule-based widget in the app’s dashboard:
Go to Merchandising > Recommendation > Widgets.
Click Add new widget.
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 types.
4. On Recommended product settings, select Rule-based recommendation.
5. 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
The list of product metafields is linked to the metafields added on the Settings > Metafields and Metaobjects feature. Remember to sync recent updates when you add a new metafield from Settings > Metafields and Metaobjects.
Once enabled, you can choose which metafield values to ignore.
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.
💡 The list of product metafields is linked to metafields added in Settings > Metafields and Metaobjects. Remember to sync recent updates when you add a new metafield.
6. For Same collection, Same tags, and Same product metafield value rules, configure the filtering logic (see below).
7. Start customizing your recommendation widgets.
Configure filtering logic (Include or Exclude)
For the Same collection, Same tags, and Same product metafield value rules, you can choose whether to include specific values or exclude specific values from the input data for the model.
Same collection
Once you enable this rule, configure two dropdowns:
Dropdown | Description |
Filtering logic | Choose Include collections (default) or Exclude collections. |
Include the following collections (shown when logic is set to Include) | Select which collections to include. Default is All collections, followed by a list of your store's collections. |
Exclude the following collections (shown when logic is set to Exclude) | Select which collections to exclude from the input data. |
Same tags
Once you enable this rule, configure two dropdowns:
Dropdown | Description |
Filtering logic | Choose Include tags (default) or Exclude tags. |
Include the following tags (shown when logic is set to Include) | Select which tags to include. Default is All tags, followed by a list of your store's tags. |
Exclude the following tags (shown when logic is set to Exclude) | Select which tags to exclude from the input data. |
Same product metafield value (1, 2, 3)
Once you enable this rule and select a product metafield, configure two dropdowns:
Dropdown | Description |
Filtering logic | Choose Include metafield values (default) or Exclude metafield values. |
Include the following metafield values (shown when logic is set to Include) | Select which metafield values to include. Default is All values, followed by a list of available values. |
Exclude the following metafield values (shown when logic is set to Exclude) | Select which metafield values to exclude from the input data. |
Example
A source product has tags A, B, and C.
If you set Exclude tags with tag B selected, the model treats the source product as having only tags A and C, and recommends items that match A or C.
If you set Include tags with tag A selected, the model only considers tag A from the source product, and recommends items that share tag A.
How multiple rules work together
💡 When multiple rules are enabled, the model uses OR logic. Any product matching at least one rule can be recommended.
More matches = higher rank. Products that satisfy more of your rules rank above those that match fewer.
Set priority by drag-and-drop. Higher-priority rules surface their matches before lower-priority rules. The top rule controls the first position on the storefront.
Example
You enable two rules: Same collection (1st) and Same vendor (2nd).
Recommended products include items that match either rule.
Items matching both rules rank highest.
Next, products from the same collection appear, followed by products from the same vendor.
Tutorial Video
Watch our tutorial video to learn how to set up a Product Recommendation Widget:
Feel free to reach out to our dedicated support team via chat if you have any questions or require additional assistance.