Undated
The next episode of Me, Myself, and AI features Jeff Cooper, senior director of data science at Stitch Fix.
“Shervin and I get some AI fuel fashion advice from Jeff Cooper, senior director of data science at Stitch Fix.”
Topic
Stitch Fix
16 facts from 2 episodes, in date order. These are what speakers said on the shows, each linked to the moment it was said. They aren't independently verified.
Undated
Jeff Cooper says Stitch Fix serves more than 3 million clients across women's, men's and kids' clothing.
“We serve more than 3 million clients we call them in women's, men's and kids.”
Undated
Jeff Cooper says Stitch Fix had just turned 13 years old and had recently passed 100 million fixes sent.
“We just had our 13th birthday yesterday, actually, and we just passed 100 million fixes sent pretty recently.”
Undated
Stitch Fix ships selected items to clients, who keep what they like and return the rest at no charge.
“We send them to you, uh, you keep what you like, you send back anything that you don't want for free.”
Undated
Each new Stitch Fix client is matched with a stylist drawn from the company's thousands of style experts.
“when you sign up, you're matched with a stylist, one of our thousands of style experts.”
Undated
Jeff Cooper says about 85 percent of Stitch Fix clients leave feedback on items.
“Eighty five of clients leave feedback on items.”
Undated
Jeff Cooper says Stitch Fix ships a couple hundred thousand fixes a week and employs a couple of thousand stylists.
“We ship a couple 100,000 fixes a week, and we have a couple of thousand stylists employed.”
Undated
Cooper says the Stitch Fix founder originally assembled the first fixes herself in her apartment.
“Just, you know, putting these fixes together in her apartment.”
Undated
Stitch Fix's outfit completion model was trained by stylists teaching it which items go together, so it could build outfits automatically.
“something that our stylists were teaching a model which items go together in order to help it build outfits in a fully automated way.”
Undated
Stitch Fix's Complete Your Looks feature pairs items a client has kept with other products.
“you'll see a popular feature called Complete Your Looks, which helps pick out items that you've kept that we know that you own and liked and pair them with other things”
Undated
Stitch Fix experimented with large language models early on for dynamic ad copy and product description pages.
“things like crafting dynamic ad copy or helping to improve our product description pages across all of our site.”
Undated
Stitch Fix rolled out an optional stylist note-writing template built on OpenAI's GPT-4.
“And we've rolled out a new feature with OpenAI's GPT four that enables a stylist to choose from a sort of starting place, a template.”
Undated
Jeff Cooper says the GPT-4 note feature saved close to twenty (unit unstated in the transcript) of note-writing time for stylists.
“This has saved close to twenty of note writing time for our stylists, which is a big savings at our scale.”
Undated
Cooper says Stitch Fix's outfit model aims to create tens of millions of outfits a day, too many for humans to assemble.
“we're trying to create tens of millions of outfits a day for our clients.”
Undated
Stitch Fix recently merged its separate recommendation models into one unified recommendation model.
“A really big advance for us in the last couple years was moving our models to a single unified recommendation model.”
Undated
Before unification, Stitch Fix used separate models for different audiences and parts of the client journey, such as a women-only model for Freestyle.
“Here's a machine learning model for women only for the freestyle portion of the site, the clients shopping on their own.”
Episodes