Setting up AI-based recommendation

On this page

Understanding AI-based recommendation

The AI-based recommendation is automatically generated by our AI models, which are based on products that are commonly purchased together, have similar product data, and become more accurate over time as more order and product information becomes available.

  • Note: This feature is only available for App Lib V3, please contact us for further instructions.

Model status

Here is some model status that you need to know:

  • Done and ready to use: AI models are done processing. You can use these recommendation types on your store now.
  • In process: Once we have full permission to run the AI model, processing will begin with this status. It may take some time to train the model.
  • Not sufficient data to process: It means your store doesn’t have enough data for AI-based recommendation work. At this time, please use the rule-based settings instead.
  • [Recommendation type] recommendation cannot work without read_orders and other permissions:
    • 3 recommendation types will need your permission are: FBT, Related items and Trending products

Set up AI-based recommendation

To set up an AI-based recommendation, we need the view_order and read_order permission to run data for the model.

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

  1. Go to Recommendation > Manage recommendation widgets.
  2. Click button Add new widget.
  3. On the Page type section, select Product page or Cart page > button Create (currently we only allow the AI-based for Frequently Bought Together and Related items type on the Product page and Cart page).
  4. On the step General, select recommendation type Frequently bought together or Related items > button Create.
  5. Toggle the button AI-based recommendation to enable the feature.
  6. Select the specific AI models depending on each recommendation type:
    • Frequently bought together
      • AI-based recommendations will recommend products that are more often browsed and purchased by other customers in a single transaction, based on items added to the customer’s cart on your store.

      • Based on the shopping history of all customers in your store.

    • Related items
      • You can select 1 option among 3 options:
        • Complementary products
          • Show products a user would purchase in addition to a particular product or set of products.
          • Ex: if a user is looking at toothpaste, this algorithm shows toothbrushes and dental floss.
        • Alternative products
          • Show products a user might consider as an alternative to a particular product or set of products.
          • Ex: if a user is looking at toothpaste, this algorithm shows other types of toothpaste.
        • Mix complementary products and alternative products
          • Show products that could be complementary products and/or alternative products.

          • Ex: if a user is looking at iPhone, this algorithm shows phone cases, screen protectors, and other types of iPhone.

  7. Click button Save & Next.