User Actions Model

The User Actions recommendations model utilizes user behavior to create rule-based personalized recommendations. These are effective when a strong intent is shown by users, such as abandoned carts, wishlists, and other behaviors indicating an interest in a specific product or service. User Action recommendations offer several benefits for businesses:

  • Personalized engagement
  • Precise targeting
  • Re-engagement opportunities

Example Use Cases

  • Recover lost sales with cart abandonment reminders.
  • Get back-in-stock alerts and never miss out!
  • Boost engagement with personalized campaigns from users' wishlists.
  • Re-engage users with recently viewed items.
  • Drive repeat business with gentle nudges.
warning

Warning

Mapping user actions is mandatory for the User Actions recommendations model.

Creating User Action Recommendations

  1. Go to Content > Recommendations from the left navigation. The Recommendations page is displayed.
  2. Click Create recommendation.
  3. Select the User Actions model and click Next.
  4. In the Recommendation name field, enter a name for the recommendation.
  5. In the Recommendation description field, enter a description for the recommendation.
  6. In the Catalog drop-down list, select the relevant catalog from which you wish to retrieve these recommendations.
  7. Choose the relevant user actions based on your use case from the Item where user performed drop-down list and define the activity date range. For example, Added to wishlist performed in the last 7 days. You can also exclude certain types of interacted items.

  8. In the Sort the filtered items section, sort the recommendation results by any numeric attribute. For example, price.

  9. Click Save. A recommendation is created with an 'Active' state on the Recommendations page.

By leveraging specific user actions such as abandoned carts or wishlist items, businesses can re-engage users and drive conversions.

Previous

Next

Was this article helpful?
0 out of 0 found this helpful

How can we improve this article?