Meta Platforms Technologies Products Meta Horizon Store Recommendations AI system

UPDATED MAR 7, 2025
The content you see on your Meta Platforms Technologies Products Meta Horizon Store Recommendations is selected, ranked and delivered to you by an artificial intelligence (AI) system. Within one AI system, multiple machine learning models work together to deliver your experience. These models and their input signals are dynamic and they change frequently as the system learns and improves over time.

Overview of Meta Platforms Technologies Products Meta Horizon Store Recommendations

When you view and interact with Meta Horizon Store, one of the underlying AI systems powers the Meta Horizon Store recommendations experience. When you open the Store while in the headset, on mobile, or on the web, you are taken to our Store Home Experience. The Store Home Experience allows you to navigate to different content via navigation pills or using filters. You can also browse content that is displayed in Store Home in a recommendation feed format.
How Meta Platforms Technologies Products Meta Horizon Store Recommendations works
The AI system behind Store Recommendations automatically orders content by predicting what you will most likely find relevant and interesting. Here’s how it works:
  1. Gather Inventory
    The system gathers content (e.g., Apps) eligible to be recommended. This does not include content that goes against our Content Guidelines.
  2. Make predictions
    From there, the AI system uses models to make predictions about content you may find most relevant and interesting.
  3. Rank content by score
    Finally, the system calculates a relevance score and ranks the content based on this score. Content that the system predicts will be most useful or relevant to you are shown higher in Store surfaces (e.g., Feed, Spotlight, Pills, Navigation). The system also tries to ensure that your Store has a balance of mixed types of content (e.g., different genres, categories, etc.). That means, for example, you likely will not see multiples of the same content types in a row, but rather a variety.
How to customize what you see
Your experience on Meta Platforms Technologies Products Meta Horizon Store Recommendations is personalized based on your activity, and you have options to control or customize what you see. Below, we describe how to do this with different in-product features. Options shown here may not be available to everyone.
Filter the apps
You can filter content by Sort, Genre, Rating, Age Rating, Pricing, Game Mode, Language, Player Mode, Controller, and Sale Type.
Flag an app
You can flag apps that go against our Content Guidelines, our Code of Conduct for Virtual Experiences or any other policy violation.
How the AI delivers content to you
We want you to see content you enjoy and find interesting. To achieve this, the AI system has models that help it make predictions about content you'll find most relevant and valuable. These prediction models use underlying input signals to help select content you're most likely to engage with.
Below are some of the significant predictions–and input signals that inform them–that we use in this AI system.
How likely you are to purchase content
Signals influencing this prediction include:
  • How many times you’ve viewed an app
  • Aggregated events like total count of impressions, clicks, installs, etc.
  • How often you use the Meta Horizon mobile app or headset
  • Features of the app like description, title, genre, price, etc.
  • Features of the app like description, title, genre, price, etc.
How likely you are to click content
Signals influencing this prediction include:
  • How often you use the Meta Horizon mobile app or headset
  • How many times you’ve viewed an app
  • Aggregated events like total count of impressions, clicks, installs, etc.
  • Similarities between the app and others you've acquired
  • Features of the app like description, title, genre, price, etc.
For users in parent-managed Meta accounts, a more limited set of input signals may be used, depending on their settings.