How Stitch Fix Relies on Data Science to Build the Perfectly Personalized eCommerce Experience
Digging into the data behind the future of eCommerce
Style is a very personal part of what makes someone who they are. The way you dress is a reflection of who you are or who you want to be, and what speaks to you may be totally foreign to the next person. Knowing all of that, it’s understandable if you believe that something as personal and experience-driven as style could never be boiled down to data points or plugged into an algorithm. But… you’d be wrong.
At Stitch Fix, a combination of human stylists and powerful A.I. and behind-the-scenes technology has created a winning model that delivers a personalized online shopping and styling experience straight to clients’ homes. A powerful data science team is one of the key reasons that Stitch Fix has been able to launch its valuation into the billions and Stephanie Yee is the VP of Data Science and one of the leaders of that team at Stitch Fix.
“Stitch Fix is really trying to distill a lot of these things that are ultimately very difficult to categorize into what we would call a latent space, but really to say, ‘Okay, we have something like style, but style is not what lunch table did you sit at in high school,’” Yee said. “It’s really a form of self-expression. And because people are so different, we need to be able to use data science to quantify where people are on a spectrum versus what category they’re in.”
Practically, what does that look like? Mostly, it’s a process of gathering feedback from customers and then letting the algorithms and the human stylists do the work to create a personal assessment for each customer.
That assessment can turn into a box of goodies delivered to a customer’s door, but it can also be a way to turn an online shopping experience into something more personal by delivering data in an easily-digestible way.
Yee explained that Stitch Fix is exploring the many uses of GPT-3, which is taking long tail natural language that is normally hard to process, and turning it into content that is helpful to a potential customer.
“GPT-3 is a really great way to translate information into the format that people are used to absorbing information in, which is text,” Yee said. “I think that it’s especially important going back to the idea of if you take a shirt, the specs of a shirt are not particularly helpful to a shopper. They can be helpful to a computer, but it’s like, ‘Okay, the sleeve is 13 and a half inches, who cares?’ And GPT-3 is able to almost add [information] in a way that would have been incredibly difficult before. It’s able to translate some aspects of an item into what that actually means in someone’s everyday life.”
Knowing how to implement and utilize groundbreaking tech is important for any data scientist who is working in eCommerce. But, according to Yee, technical skills are not the first thing she looks for when she’s hiring talent.
“When hiring a data scientist, we need them to have a good understanding of statistics, oftentimes machine learning, computer programming, sometimes software engineering,” Yee said. “But really, the core thing that we think about is can they frame a problem? How do they think about problem framing? Because what will often happen… is people will very valiantly answer the wrong question. And it’s not their fault that they’re answering the wrong question, it’s just the wrong question was asked. So what we really encourage folks to do and what I think the most effective data scientists do when they’re empowered to do so, is if people pose a problem to solve, it’s actually okay to say, ‘Okay, let’s take a step back. Let’s dig into this a little bit and figure out like is this posed in a way that can lend itself to the full suite of potential solutions?’”
At Stitch Fix, the big problems can change on a dime, like in 2020 when COVID-19 forced the company to adapt all of its forecasting models. But with the right team and technology in place, Yee said the company was able to take the challenges in stride.
To find out how, check out her interview on Up Next in Commerce.
— -
Up Next in Commerce is brought to you by Salesforce Commerce Cloud. Learn more at salesforce.com/commerce
