Facebook Marketplace AI system

UPDATED MAR 12, 2025

The content you see on your Facebook Marketplace 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 Facebook Marketplace

When you view and interact with Facebook, including Facebook Marketplace feed, one of the underlying AI systems recommends relevant Marketplace listings. For example, you can see items for sale in categories such as home goods, pet supplies and sporting goods. Your feed might also include other recommendations, such as sellers and content you may be interested in.

Note: Your Marketplace feed might also include boosted listings and advertisements. That content is not powered by the AI we describe in this system card.

How Facebook Marketplace works

The AI system behind Facebook Marketplace feed automatically determines which posts show up in your feed by predicting the listings, sellers and content you’re most likely to be interested in. These predictions are based on a variety of factors, including how you’ve interacted with previous listings and with Facebook content. Here’s how it works:

Gather inventory
First, the system gathers listings to show you from a variety of sources using different methods. For example, products may be included in your feed based on how recently the product was listed for sale. Products may also be included in your feed based on relevance, by comparing the product characteristics to your activity history.
The AI system generally hides product categories you’ve chosen to block and then produces a subset of listings for further processing. This does not include listings that were reviewed and subsequently rejected based on Meta’s Commerce Policies. Then, the system sends around 1,000 listings on to the next stage.
Leverage signals
Now, the system considers a variety of input signals based on your activity on Facebook, including Facebook Marketplace. These signals may also include location, category, condition or price of the product or seller.
Make predictions
From there, the AI system has models that help it make predictions about listings, sellers and content you’ll find most relevant. The system applies certain integrity processes to help reduce the distribution of content that is fraudulent, low-quality or that goes against our Commerce Policies. The system also hides content that—while not against Commerce Policies—you may not want to see, based on other listings you’ve hidden.
Rank listings by score
Finally, the system calculates a score for each listing, seller or content and puts them in order by this score. Listings that the system predicts will provide more value for you are shown to you first.

How to customize what you see

Your experience on Facebook Marketplace 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.

Browse in a non-personalized way

You can browse Marketplace in a way that’s not personalized specifically to you. Learn more.

Report listing

You can report a listing, which triggers a review that will remove the listing if it goes against our Commerce Policies.

Choose categories

Marketplace lets you choose categories and subcategories to browse and search different listings. Some categories have category-specific filters, such as “vehicle type” in the “vehicle” category.

Set location

You can set the location or radius of where you want to search for local listings in your country. This location can be different from the one on your Facebook profile.

Hide listing

You can hide listings so they no longer show up when browsing or searching Marketplace. This also decreases the likelihood of seeing similar listings in the future.

Identify interests

Marketplace may prompt you to identify your preferences and interests in areas such as specific categories or brands. While optional, these choices customize your experience so that you'll see more of what you’re interested in.

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.

Whether or not you will cross out the listing