Instagram chief Adam Mosseri has revealed how its feed, feels and stories algorithms work. He says 'Instagram doesn’t have a singular algorithm that oversees what people do and don’t see on the app. We use a variety of algorithms, classifiers, and processes, each with its own purpose. We want to make the most of people’s time, and we believe that using technology to personalize everyone’s experience is the best way to do that.' 

How they Rank Feed:

• Users' activity. Posts users have liked, shared, saved or commented on help Instagram understand what they might be interested in.
• Information about the post. These are signals both about how popular a post is – how many people have liked it and how quickly people are liking, commenting, sharing and saving a post – and more mundane information about the content itself, like when it was posted, and what location, if any, was attached to it.
• Information about the person who posted. This helps Instagram get a sense of how interesting the person might be to the users and includes signals like how many times people have interacted with that person in the past few weeks.
• Users' history of interacting with someone. This gives Instagram a sense of how interested users are generally in seeing posts from a particular person. An example is whether or not users comment on each other’s posts.

How they Rank Stories:

• Viewing history. This looks at how often users view an account’s stories so Instagram can prioritise the stories from accounts it thinks users don’t want to miss.
• Engagement history. This looks at how often users engage with that account’s stories, such as sending a like or a DM.
• Closeness. This looks at users' relationship with the author overall and how likely they are to be connected as friends or family.

How they Rank Explore:

• Information about the post. Here Instagram is looking at how popular a post seems to be. These are signals like how many and how quickly other people are liking, commenting, sharing, and saving a post. These signals matter much more in Explore than they do in Feed or in Stories.
• Users' activity in Explore. These are signals like posts users have liked, saved, shared or commented on and how they've interacted with posts in Explore in the past. If they interact with a specific type of post, Instagram tries to show them more content similar to the original post they interacted with.
• Users' history of interacting with the person who posted. Most likely the post was shared by someone users have never heard of, but if they have interacted with them that gives Instagram a sense of how interested users might be in what they shared.
• Information about the person who posted. These are signals like how many times people have interacted with that person in the past few weeks, to help find compelling content from a wide array of people.

How they Rank Reels:

• Users' activity. Instagram looks at things like which reels users have liked, saved, reshared, commented on, and engaged with recently. These signals help Instagram understand what content might be relevant to users.
• Users' history of interacting with the person who posted. As with Explore, it’s likely the video was made by someone users have never heard of, but if they have interacted with them, that gives Instagram a sense of how interested users might be in what they shared.
• Information about the reel. These are signals about the content within the video such as the audio track or visuals in the video, as well as popularity.
• Information about the person who posted. Instagram considers popularity signals such as the number of followers or level of engagement to help find compelling content from a wide array of people and give everyone a chance to find their audience.

For more information visit instagram.com.