How TikTok Recommends Videos #ForYou

TikTok released a blog post today explaining how recommendations are delivered to the For You feed, which is central to the TikTok experience and where most users spend their time.

Part of the magic of TikTok is that there’s no one For You feed – while different people may come upon some of the same standout videos, each person’s feed is unique and tailored to that specific individual.

The blog post delves into explaining the basis of this, which is a recommendation system. Recommendation systems are designed to help people have a more personalized experience — they suggest content after taking into account user preferences as expressed through interactions with the app, like posting a comment or following an account. On TikTok, the For You feed system recommends content by ranking videos based on a combination of factors – starting from interests you express as a new user and adjusting for things you indicate you’re not interested in, too – to form your personalized feed reflecting preferences unique to each user.

However, by optimizing for personalization and relevance, there is a risk of presenting an increasingly homogenous stream of videos. To keep the For You feed interesting and varied, TikTok’s recommendation system works to intersperse diverse types of content along with those you already know you love.

Ultimately, the For You feed is powered by users’ feedback. The system is designed to continuously improve, correct, and learn from an individual’s engagement with the platform to produce personalized recommendations to inspire creativity and bring joy with every refresh of your For You feed.

What factors contribute to For You?

On TikTok, the For You feed reflects preferences unique to each user. The system recommends content by ranking videos based on a combination of factors – starting from interests you express as a new user and adjusting for things you indicate you’re not interested in, too – to form your personalized For You feed. 

Recommendations are based on a number of factors, including things like:

• User interactions such as the videos you like or share, accounts you follow, comments you post, and content you create.
• Video information, which might include details like captions, sounds, and hashtags.
• Device and account settings like your language preference, country setting, and device type. These factors are included to make sure the system is optimized for performance, but they receive lower weight in the recommendation system relative to other data points we measure since users don’t actively express these as preferences.

All these factors are processed by our recommendation system and weighted based on their value to a user. A strong indicator of interest, such as whether a user finishes watching a longer video from beginning to end, would receive greater weight than a weak indicator, such as whether the video’s viewer and creator are both in the same country. Videos are then ranked to determine the likelihood of a user’s interest in a piece of content, and delivered to each unique For You feed.

While a video is likely to receive more views if posted by an account that has more followers, by virtue of that account having built up a larger follower base, neither follower count nor whether the account has had previous high-performing videos are direct factors in the recommendation system.