Pinterest is beta-testing a way to enable users to narrow down their beauty-related search results by skin tone.
The test kicked off with four palette options, each representing a range of skin tones, and Pinterest users will be able to select one of them to filter their search results for beauty ideas.
Pinterest said that among users who engage with beauty-related content on its network:
- 70 percent discover, search for or create boards containing looks or styles they can use every day.
- 60 percent learn how to create a new look or style for a special occasion.
- 40 percent show stylists Pins or boards.
- 40 percent create boards or wish lists for items they wish to purchase.
- 34 percent find specific products for immediate purchase (within the next month).
In addition, 89 percent of weekly active Pinners said Pinterest offers ideas of beauty and grooming products to shop for, and 70 percent discovered new products in those categories on Pinterest.
Engineer, search quality Laksh Bhasin provided more details on the beta-test in a blog post, writing, “We heard from Pinners that they couldn’t always find what they were looking for when searching for hair and beauty ideas, so we wanted to address this problem, starting with skin tone ranges. The skin tone ranges experiment enables you to customize your search results by a skin tone range. We’re starting with four palettes, and each represents a range of skin tones. As our technology improves and we gather more feedback from Pinners, we plan to expand the ranges to more skin tones.”
He continued, “The most accurate way to detect a skin tone in a Pin’s image would be to have a human label every single Pin image according to a scientific skin tone palette. But with billions of unique images, and many more created each day, that’s an expensive approach that would be hard to scale.”
Bhasin said Pinterest used a third-party facial artificial intelligence library from ModiFace in its beta-test. ModiFace specializes in augmented reality and machine learning for beauty applications, and it was able to produce algorithms with the help of “deep neural networks.”
He also stressed Pinterest’s commitment to privacy, writing, “If you tap a skin tone range, we do not store this information or use it to build a profile for you. This means you’ll need to tap a skin tone range each time you search. We also don’t use this information to target ads. We do not attempt to predict a user’s personal information, such as ethnicity.”