What types of features does Promoted support?

Promoted supports many different FeatureFeature - Variable in a machine learning model, including attributes of User, Content, etc. types to make recommendations. Here, we list the major Feature DomainFeature Domain - Feature domains help engineering design feature retrieval and integration systems to estimate the value of (Content, User, Context) matching. The most interesting features are “domain interaction features,” or information at the intersection between two or more feature domains. The top domains are:s, provide some examples, and describe how to send these features to Promoted. The top domains are:

Content Item features

Content item features are stable properties of the item to show. These can be attributes like color, a list of labeling tags, media like images, or free text like title or description.

User features

User features are stable properties of the user viewing the content. The user may be anonymous, in which case there are no or limited user features. User features can be user attributes like age and gender, lists of interests or behaviors that may be computationally inferred, or user-provided settings.

Context features

Context features are properties about where the items will be shown and to whom. For example, a search query, the page address, the mobile device type, geographic location, or time.

Interaction features

Interaction features require the intersection between two or more domains. Interaction features tend to be the most powerful features in scoring (item, user, context) matches. Domain intersections include:

  • (Item x Context): query match or relevance scores
  • (Item x User): personalization scores, past user history with this item, collaborative filtering
  • (Context x User): search filters, home feed categories
  • (User x Item x Context): other recommendation models


See How to send features to Promoted? for integration details.

Did this page help you?