Pinterest is testing a skin tone filter to help narrow search results
Pinterest is testing a new search feature that allows users to narrow their search results by skin tone range.
The social platform says it is trialling the feature to help users find more relevant results, after discovering that 70% of people use Pinterest to find everyday looks and style ideas they want to try.
The firm said the new filter could help users cut through the vast amount of content on the site and find the beauty tips they’re looking for more easily.
“More than 200 million people use Pinterest every month. Our product reflects the global interests and tastes of people all over the world, with more than 100 billion ideas to explore,” the site’s engineering team said in a post to Medium.
“However, it’s not always easy to find the most relevant results. The majority of queries on Pinterest are less than three words, which presents an interesting serving challenge. In addition, our current ranking algorithms are heavily influenced by what the majority of people have engaged with over time. This means that some Pinners have had to work harder to find what they were looking for.”
Pinterest said creating the filter was a challenge because detecting skin tone in posts can be hindered by lighting, shadows and other factors.
To combat this the engineers turned to machine learning, and a third-party AI-powered face library app called ModiFace, which specialises in augmented reality and machine learning in beauty applications.
All this software was used to create an algorithm to detect skin tones, training it on how different lighting affects skin tone appearance.
“This initial version of skin tone ranges filters content based on skin tone darkness or lightness using four ranges, each with some amount of overlap,” the engineers said.
“On the front end, skin tone ranges are shown to users as quadrants, so that it’s clear each palette actually encompasses a range of skin tones. To ensure a good experience for Pinners, skin tone ranges are currently only shown for a predetermined list of common hair and beauty queries.”
The team now says its work on the filter will focus on improving its accuracy, as well as thinking of other ways to narrow search results beyond skin tone.