Skip to main content

Going deep into the Instagram’s feed ranking algorithm

Going deep into the Instagram’s feed ranking algorithm

Ranking algorithms means feed posts showing up based on what Instagram thinks you want to see and not just the newest posts first.

Let's check the Instagram’s giant feed handling – 

They never revealed how the feed algorithm worked until they called upon a group of reporters to their San-Francisco office and pulled the curtains off from the Instagram feed ranking algorithm.

They explained the reporters that there were three factors where an individual’s engagement to the app is taken care of, the three being: -

  1. Interest - How much an individual is concerned about a post
  2. Timeliness - How recent the posts are uploaded
  3. Relationship - The person or account you regularly interact with.

Along with these three criteria’s (which played an important role) in any Instagram feed ranking. There are more to add:

  1. Frequency - How often user opens Instagram.
  2. Followings - Content from all accounts a user follows.
  3. Usage - How long an individual spends time on Instagram determines if you’re just seeing the best posts during that short session.

The order of photos and videos in an individual’s feed will be based on the likes they’ll be getting on their content, their relationship with the person posting and the timeliness of the post.

Combining all the criteria’s and the machine learning algorithm, improves the individual user profile to show recent and most relevant posts.
It categorises based on the hashtags or the genre the individual looks more frequently so that the post might rank higher than the regular genre’s. 

Some posts from last week might not interest you as much as something from an hour ago, so Instagram will likely show you more recent posts rather than posts from a few days or weeks prior – Irrespective of the post getting a lot of attention.

This implies that recent posts likely rank higher in your feed and that the timing of your post is still relevant.
No matter how many accounts you follow. Instagram feed will favor videos over photos or vice versa as per your timeliness.

New posts are visible only to a smaller number of people and It will measure how fast and how often that these small percentage of audience will react (looks at, likes, comments, shares and saves) with your posts, videos and stories.
Here is the diagrammatic representation of the above algorithm.

That’s it!

If you have any insights, corrections or recommendations when it comes to how the Instagram Algorithm works, please email me at

Thank you for taking out some time to read my article. Appreciate It!


  1. The effectiveness of IEEE Project Domains depends very much on the situation in which they are applied. In order to further improve IEEE Final Year Project Domains practices we need to explicitly describe and utilise our knowledge about software domains of software engineering Final Year Project Domains for CSE technologies. This paper suggests a modelling formalism for supporting systematic reuse of software engineering technologies during planning of software projects and improvement programmes in Final Year Projects for CSE.

    Software management seeks for decision support to identify technologies like JavaScript that meet best the goals and characteristics of a software project or improvement programme. JavaScript Training in Chennai Accessible experiences and repositories that effectively guide that technology selection are still lacking.

    Aim of technology domain analysis is to describe the class of context situations (e.g., kinds of JavaScript software projects) in which a software engineering technology JavaScript Training in Chennai can be applied successfully

    The Angular Training covers a wide range of topics including Components, Angular Directives, Angular Services, Pipes, security fundamentals, Routing, and Angular programmability. The new Angular TRaining will lay the foundation you need to specialise in Single Page Application developer. Angular Training


Post a Comment

Popular posts from this blog

Auto Scaling DynamoDB

Those of you who have worked with the DynamoDB long enough, will be aware of the tricky scaling policies of DynamoDB. It allows user to explicitly set requests per second (units per second, but for simplicity we will just say request per second). User can do so for read as well as write operations. Anytime user can increase or decrease the provision capacity from DynamoDB web console and it will reflect immediately. Sounds all good....... Or not? What if you set provisioned capacity to 50 req per second but load on the server crosses 100 req per second? Requests gets throttled!! Mostly times out. What's worse? This can cause requests getting queued up in your web server. Which can potentially bring your entire server down. What if you set provisioned capacity to 1000 req per second but load on the server is only 100 req per second through out the day? You lose your hard earned money for remaining 900 req per second. What if you set it to 1000 req per sec and then realis

StackDriver Integration with AWS Elastic Beanstalk - Part 1

Stack Driver Setup Step 1: Create stackdriver project Navigate to  After logging in you will be redirected to project creation page. To manage multiple environments of your application its advisable that you create just two projects. One for production env and other one for non-prod. Even though you might have multiple non-production environments, but having one stackdriver project per application-env is overkill. So, lets start with production project. For this tutorial, I'll create CodeHooDoo-Prod project. Once the project is created, StackDriver will ask you to link your AWS account resources to it for monitoring.  But as AWS CloudWatch has good monitoring and alerting support you can skip this one. Keep clicking continue until you get to monitoring console. Click on the logging. This is where you will get all the logs from your application server. Step 2: Download authentication key Navigate backt to .