Users-for-Item Recommendations

Users-for-item recommendations retrieve the set of users who have interacted with an item, weighted by the number of interactions. This can be useful for community-driven use cases or for marketing campaigns. For example, on your organization’s intranet, clicking a search result could display the item plus a list of colleagues who have interacted with the same item.

This is one type of collaborative recommendation.

To enable this recommendation method, you only need to create a new collection and modify the configuration of the default recommender job, as explained below.

How to enable users-for-item recommendations
  1. Navigate to Collections > Collections Manager.

  2. Click New

  3. Enter a collection name, such as <main-collection>_users_for_item_recommendations.

  4. Click Save Collection.

    You can safely disable signals for this new collection.
  5. In your main collection, verify that signals and recommendations are enabled.

  6. Navigate to Collections > Jobs.

  7. Open the <collection>_item_recommendations job.

    Alternatively, you can create a new ALS Recommender job for these recommendations.

  8. Click Advanced.

  9. In the Users-for-items Recommendation Collection field, enter the collection name <collection>_users_for_item_recommendations.

  10. Click Save.