Instagram Explore Strategy
On the Explore Page, most posts come from accounts you don’t follow. So, the AI relies heavily on your past behavior to guess what you might like.
It looks at what you’ve interacted with before, then pulls in similar content to test what holds your attention. (Fun fact: Explore has the most ranking signals of any surface)
Here are the ones that matter most:
Your likelihood of following the creator: Instagram looks at how often people follow a creator from a specific post, plus how recently you viewed that creator’s profile.
Your likelihood of viewing the post for at least five seconds: If people linger on a post (even a few seconds) that’s a sign it’s grabbing attention. The system looks at how long you’ve spent on similar posts in Explore.
Your likelihood of finishing a video (watching 95% or more): High completion rates are a huge deal in Explore. When lots of people watch a video almost all the way through, the system assumes more people might enjoy it too.
For the complete list of 36 ranking signals used to build your Explore Page, check out Meta’s Transparency Center.
Optimize your content for Instagram SEO
While hashtags have value, social SEO reigns supreme. “It’s extremely important to write keyword-rich content to enhance content indexing by Instagram’s AI,” says Fung.
For example, this Reel uses keywords and relevant hashtags like “beginner arm workout,” “workout for women,” and “toned arms workout” to help reach the creator’s target audience.
Explore tip beginner arm workout with relevant and searchable hashtags
Source: @caitiejunefit
Who this is for: Brands, businesses, and creators
Why it works: “It’s in your best interest to ensure all aspects of your brand/content are constantly optimized,” Fung explains. Using keywords in your bio and captions helps the platform determine what your content is about and who should see it.
How to do it: Use alt text whenever you can and ensure you’re including relevant keywords in your Instagram captions and hashtags.
Instagram Explore AI system
UPDATED JUN 22, 2026
The content you see on your Instagram Explore 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 Instagram Explore
When you view and interact with Instagram, one of the underlying AI systems fetches media (photo and video) based on user's engagement history and delivers media according to user's preferences.
How Instagram Explore works
The AI system behind Explore fetches quality and personalized media through three stages: retrieval, early-stage ranking, and late-stage ranking.
Retrieval
The retrieval stage is responsible for selecting a set of candidate items (in this case, photos and videos) that are relevant to the user's interests. The system uses a variety of techniques to retrieve candidates, including item collaborative filtering, personalized PageRank, and two tower sparse network sourcing. The fetched media contain sources from author-based sources (media from authors that you've engaged with) and media-based sources (media similar to media you've engaged with). At the end of the retrieval stage, up to 1500 media are fetched.
Early Stage Ranking
The early stage ranking stage is responsible for narrowing down the set of candidate items selected in the retrieval stage to a smaller set of the most promising candidates. This stage involves a two-tower neural network that uses both media features and user features to calculate the similarity between them. At the end of this stage, the top 100 media are passed to the next stage.
Late Stage Ranking
The late stage ranking stage is responsible for generating a final list of recommended items for the user. This stage typically involves applying multi-task multi-label neural network (a more complex machine learning model) to rank the remaining candidate items based on their likelihood of user engagement such as like and save. The final list of recommended items is then presented to the user in the Explore grid.
How to customize what you see
Your experience on Instagram Explore 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.
Not Interested
If you don’t want to see more of a certain type of content, you can select “Not Interested” in the three-dot overflow menu on an individual post. The system will attempt to filter out similar content in the future.
Tune Your Algorithm
You can tell us the types of content you’d like to see more or less of by using the Tune Your Algorithm feature.
Like
Click on "Like" to signal your interest in a post. The recommender system will recommend media similar to the ones you've liked
Report
If you see content you think goes against Instagram's Community Guidelines, you can report it.
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.
Recommender One
Recommender Two
Recommender Three
Recommender Four
How likely you are to follow the author of a post
Signals influencing this prediction include:
The amount of time you’ve spent on Explore viewing posts from post’s author in recent past
How many times you've seen short, squared reel in Explore
How many follows button clicks received on a post in Explore
The amount of time you’ve visited post’s author’s profile in recent past
How many authors you have followed
How likely you are to spend more than five seconds viewing a post
Signals influencing this prediction include:
The amount of time you've spent watching short, squared post on Explore
How many people have seen the post on Explore
The amount of time you’ve spent on Explore viewing posts from post’s author
How likely you are to watch more than 95% of a video
Signals influencing this prediction include:
How many people have watched more than 95% of the video
The amount of time you've spent watching short, squared post on Explore
The amount of time you’ve spent on Explore viewing posts from post’s author
How many people have seen the post on Explore
How likely you are to click “Not Interested” on a post
Signals influencing this prediction include:
How many short, squared posts you've clicked in Explore to view in full screen
How many times the post has been seen on Explore
How many short, squared posts you’ve clicked not interested in the recent past
How many authors you’ve seen and clicked not interested
how likely you are to comment on a post
Signals influencing this prediction include:
How many times you've seen short, squared video posts in Explore
How many times the post has been clicked on Explore
How many times you’ve commented on posts from post’s author
How many comments the post received
How likely you are to “like” a post
Signals influencing this prediction include:
How many reels you have liked
How many posts you have liked in recent past
How many times you've seen the short, squared posts in Explore
How likely you are to reshare a post
Signals influencing this prediction include:
How many times the post has been clicked on Explore
Where data privacy laws permit, the posts you've reshared previously and the authors of those posts
The amount of time you’ve spent on Explore viewing posts from post’s author
How many times the post has been seen on Explore
How likely you click and also engage with a post
Signals influencing this prediction include:
How likely you will scroll down to the next post
How likely you will click on a post
How likely you will spend X number of seconds viewing a post
how likely use will interact with the post - for example, like, save, follow, etc
How likely you are to save a post
Signals influencing this prediction include:
How many people have seen the post on Explore
How many posts you’ve saved in Explore in recent past
How many posts you’ve saved in recent past
How likely you are to click one of the short, squared post in Explore to view it in full screen
Signals influencing this prediction include:
How many short, squared posts you’ve seen in Explore
Which authors' profiles you've clicked in the recent past
How many people have clicked on the post in Explore to view in full screen
How many people have clicked after being shown the post in Explore
Meta
Policies
Community Standards
Meta Advertising Standards
Other policies
How Meta improves
Age-Appropriate Content
Features
Our approach to dangerous organizations and individuals
Our approach to the opioid epidemic
Our approach to elections
Our approach to misinformation
Our approach to newsworthy content
Our approach to Facebook Feed ranking
Our approach to explaining ranking
User control: How to shape your experience on Meta’s platforms
Accessibility at Meta
AI at Meta: Transparency about our training data
Research tools
Content Library and Content Library API
Ad Library Tools
Other research tools and data catalogue
Enforcement
Detecting viol
