How Pinterest makes its 80 million beauty-related searches less racist #AI

  • Last month, the social media company launched a new search that uses AI and machine learning to show Pinners more relevant results when looking for hair inspiration.
  • Back in 2018, Pinterest launched a tool that lets users narrow down their search by skin tone ranges: Whether they’re shopping for a new foundation or pulling up inspiration for eyeshadow, Pinners are presented with a more personalized feed that reflects how they look.
  • The new search is powered by an underlying computer vision model that’s trained on a diverse set of hair-related images. Over time, the model learns to associate certain pixels with certain types of hair patterns. The overarching goal was to ensure AI fairness from the very first step in development.
  • The Pinterest team is working on rolling it out to other markets, where cultural nuances may dictate the need for more hair patterns and different definitions of beauty.

[Via]

Sign Up for nextbigwhat newsletter

The smartest newsletter, partly written by AI.

Download Pluggd.in, the short news app for busy professionals