Pinterest has announced a new initiative that will allow beauty consumers to more easily find relevant beauty ideas in search. Rolling out in beta, Pinterest is testing an inclusive discovery feature to narrow beauty search results by skin tone range. Launching with four palette options, each palette represents a range of skin tones.

In a partnership with L’Oréal-owned ModiFace, Pinterest taps into a third-party Face AI library, utilizing ModiFace’s augmented reality expertise, which produced successive algorithms for skin tone detection. As new Pins are added to the system, Pinterest will incrementally run the skin tone detection algorithm on just those, so as to increase its coverage of skin tone data and improve results.

Pinterest added that it does not store user information or use it to build their profile or to target ads. This means users will need to tap a skin tone range each time it’s searched.

Once the beta experiment rolls out to all users, future goals will focus on improving the accuracy of results and bringing the experience to more platforms.

“We’ll try out new methods of query rewriting and blending in actionable content and hope to improve our search ranking models in order to better take into account the selected skin tone. To make experimentation easier with new skin tone detection algorithms, we’ll have to make a few backend changes to allow us to index multiple detected skin tones and run A/B experiments more easily,” wrote Laksh Bhasin, Pinterest Engineer, Search Quality, on engineering blog, Medium.

The Connected Consumer is a feature series focusing on digital as it touches the beauty consumer. On November 14, CEW will host its second annual The Connected Consumer Conference, presenting speakers from the most relevant brands, retailers and forecasting agencies discussing the latest trends in digital and social media.