Recently, Facebook hosted the “Machine Learning @ Scale event, explaining how the Instagram algorithm works behind the scenes of its social platform…
At the latest Machine Learning @Scale event, insiders from social media giant Facebook, took some time to explain how the Instagram algorithm functions. The event features several of the best and brightest minds in machine learning and artificial intelligence.
Facebook Explains How the Instagram Algorithm Works
Specifically, the event looks into how to implement these technologies on a large scale. Such massive use requires enormous resources and highly technical processes to achieve accuracy.
“Machine Learning @Scale is an invitation-only technical conference for data scientists, engineers and researchers working on large-scale applied machine learning solutions. ML is critical to a broader range of systems than ever before: from augmented reality to language technology and everything in between. Today’s ML practitioners face daunting scale challenges since their systems and services may be used by millions if not billions of customers,” the @Scale Conference website states.
At the event, Thomas Dimson, a software engineer at Instagram, explained how the social platform processes its feed algorithm. Dimson pointed out four crucial metrics of how Instagram defines relevance to dictate the way content ranks inside the feed:
- Other users’ content you like
- People you directly message
- People you search for
- People you know in real life
The weight of each metric was not disclosed; so, it’s unknown which are the most important. The video presentations are available on the Facebook code blog.
In January, Instagram Stories live video launched worldwide, to challenge rivals Periscope and Snapchat directly for market share. The social media platform started testing shoppable photo tags back in November of last year.
Thanks for taking a few moments of your time to read this; if you like this information, please share it with your friends!