Facebook is developing a universal product recognition model that uses AI to identify items users put up for sale on the platform.
This AI system is meant to improve the way people buy and sell products on the company’s Marketplace and across all of Facebook’s platforms.
Facebook notes that most product recognition models work well for a single product, such as fashion or home decor. The social media giant outlined that this type of system wouldn’t work for Facebook, because people buy and sell products across dozens of categories, ranging from SUVs to shoes to side tables.
The company needed a single model to correctly identify products across all categories. Facebook notes that this meant that it needed to aggregate a massive number of data sets into a single model.
This can be quite challenging, since it can get difficult to optimize parameters for one task without reducing the effectiveness of another. For instance, optimizing a model to recognize cars well might mean that it can’t recognize patterns on clothing as effectively.
“I want to build something that ultimately feels like having one of your best friends with you whenever you get dressed, shop, want a recommendation, or simply need some inspiration,” Tamara Berg, a Facebook research scientist, wrote in a blog post.
Facebook says it essentially wants to use these AI techniques to transform online shopping for everyone on its platforms through personalization. It’s currently unknown when we’ll start to see these models come into play on the platform, but it’ll certainly be helpful once they do.
Image credit: Facebook