Pinterest announced new changes that enable users to filter hair and beauty search results depending on desired skin tone, on April 27, 2018.
Pinterest aims to make it easier for users to find what they are looking for. The platform conducted a survey and found that 70 percent users used its service to find and save everyday looks and styles, and thus rolled out its new update.
Pinterest made use of a machine learning system from ModiFace, a third-party beauty app. The ML already had a suitable facial data library for artificial intelligence use, however, Pinterest trained the algorithms in a way to not mistake reading white skin in dark shadow as dark skin tone, alongside correcting other mistakes.
Pinterest also promises its customers that it will not save search results as well as show ads depending on the searched for skin tones. The social media platform rolled out this feature in beta, the company says.
“Our future work will generally 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. Lastly, skin tones are just the start of building a more inclusive search. We hope to help Pinners find more personalized results by offering more ways to narrow your search.” said Laksh Bhasin, a Pinterest engineer in charge of search quality.