How Pinterest Built One of Silicon Valley’s Most Successful Algorithms

Image and text:

This Medium article talks about a modification Pinterest’s algorithm for its feed. It is interesting to see how tech companies are molding themselves based on true human reactions that come from their users, with the popular and necessary purpose of generating more tailored content. Pinterest has been facing some problems regarding bias and how they channel content towards their users based on two simple questions at the time they create their profiles: their age and gender. Pinterest, like other tech giants such as Facebook and Twitter, want interactions to be more humane and substantial.

The company’s main goal in its first year as a public company is to diversify its algorithm enough and grow beyond its user base of white suburban women. The most complex part of this process is to achieve this goal without alienating their loyal crowd and, at the same time, not stereotyping newcomers. The way Pinterest has been filtering content towards users in the past seems to not be satisfying users who see themselves as exceptions to the norm. “Internal data might tell you that welcoming male users with a bunch of macho images boosts activation rates. What it might not tell you is that some subset of male users is turned off, or even offended, by the implicit assumption that they’re into “man caves” or pictures of “beautiful celebrities” who are all women.”

What Pinterest is finally trying to do is placing users into finer subgroups using an algorithm that lets you modify its understanding of your browser data. A woman who just broke off her engagement might, for example, never come back to Pinterest after joining it for the first time and seeing an overflow of wedding dresses. The new algorithm, then, allows users to manually increase personalization by “turning off” subjects they are not interested in despite it being part of their online behavior. 

This update, however, goes against the general tech rule of not giving people too much power to personalize their own feeds, as that might actually decrease engagement. The idea is to provide users with a news feed that knows better than the users themselves what they want to see. Pinterest, on the other hand, admits that tech’s assumptions and bias might not always put out the best content for their users, and hopes that this new algorithm will reduce complaints and make the app work better for everyone. It is important to point out that this new feature is completely optional, but it will definitely filter out trash content for specific tribes.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s