The Future Of Work Now: AI-Assisted Clothing Stylists At Stitch Fix

Stitch Fix “fixes” awaiting opening

Stitch Fix is one of the more interesting and faster-growing retailers of the last decade. Founded in 2011, its revenues in FY20 were $1.7 billion, and it had 3.5 million active clients. It is an online personal styling service that uses AI algorithms and human stylists working in combination to make recommendations to clients of items of clothing, shoes, or accessories. The goal of the two sources of intelligence is to provide clients with a “Fix”—a mailed box of five personalized clothes choices—that are a close fit to their style, size, and price preferences. They can keep the selections, or send them back at no cost. Then the clients can either continue to receive mailed boxes, or can directly order items from the website that are recommended for them.

Stitch Fix has grown rapidly since its inception, and now offers men’s and children’s clothing as well as women’s, and serves U.S. and U.K. customers. There are now 5000 stylists across the U.S. There are also almost 150 data scientists at the company. Data science and algorithms were at the company’s core from the beginning, and they remain so. Stitch Fix was perhaps the first company to have a Chief Algorithms Officer (Eric Colson, now CAO Emeritus). They use various approaches to AI, but statistical machine learning is the primary method. Machine learning models are used to inform styling, marketing, supply chain, customer service, and many other aspects of the company’s operations.

The styling algorithms team is about a third of the data science team. The data scientists collect and use as much data as possible, including an initial style quiz for each client when they sign up to receive their first Fix. They also get considerable client preference data from a “Style Shuffle,” a Tinder-like online quiz in which clients are encouraged to give their quick reactions to a series of clothing items. All client responses and particularly rejections of mailed items are considered carefully and incorporated into styling algorithms.

PROMOTED

Tatsiana Maskalevich, Director of Data Science and Stylist

Tatsiana Maskalevich is Director of Data Science at Stitch Fix. She also styles clients—styling clients is a skill Stitch Fix teaches every single full time employee, whether you’re a data scientist, a software engineer or an accountant. It’s an unusual combination, but it helps her personally understand how algorithms and styling advice interact with each other. Algorithms make recommendations to stylists, and stylists can choose whether to accept or modify them based on their knowledge of the client and the context. Maskalevich explained that stylists both supply data to Stitch Fix’s algorithms, and use them to help make styling decisions. She commented, “The whole process of styling is a balance between data and human judgement and relationships. Stylists and customers make certain choices and not others. All of their actions are captured and used to refine recommendations. The stylist role is to understand the nuance of clients’ personal style, create a connection with clients, and build a long-lasting relationship. It takes extensive interviewing and onboarding to find the right kind of person.”

Maskalevich explained how the stylist works. “Maybe I want to start a Fix with a pair of pants. After I choose that, here are some shirts that go with it. Now stylists can create outfits for direct client shopping, and they look at outputs of algorithms for those too.” The styling algorithms team, she said, works closely with stylists. Sometimes they offer “algorithm schools” to the stylists to give them a high-level idea how the algorithms work. They explain that the models are based on many different features—size, expressed client preferences, reactions to previous Fixes, choices in the Style Shuffle, etc. Maskalevich said that it’s important for stylists to know that the recommendations are based on many different features that they would not be able to keep in their heads. There is also both automated and human coaching for stylists that lets them know how they are doing in keeping clients happy with their choices. The human coaches can discuss with the stylists their mix of art vs. science, and how it is working out in terms of satisfied clients.

Stylists are always able to override the recommendations of algorithms. The primary advantage that human stylists have over algorithms is that they know the context for the clothing. Stylist Request Notes (which clients can fill out when they order a Fix for their stylists to read before they style their Fix), are the primary vehicle for context. General statements such as “I don’t like pink shirts” or “I want a flowered dress” can be interpreted by a natural language processing (NLP) algorithm and acted upon, e.g., by adding a flower dress to the initial recommendation or purposefully removing pink shirts.

However, client statements on request notes like, “My husband is returning from being stationed overseas for 12 months,” “I’m going to a wedding that my ex will also be at,” or “I’m just about to start a new job and need to dress to impress” are so nuanced and infrequent that NLP algorithms have neither the sample size nor the compassion to adequately address them. But the stylist is able to truly understand the importance of these contextual comments. They may lead the stylist to override the recommendation of the algorithms. When the stylist and the algorithm disagree, Maskalevich explained, “We capture that data point.”

Speaking about the division of labor between algorithms and human stylists, she said,

Stylists with long tenures, she says, typically become very good at their jobs, but the algorithms improve over time as well.

When she styles clients, Tatsiana Maskalevich says she is always trying to get better at the role, but perfection is difficult to reach. “Everything is changing all the time,” she noted. “There are different style trends, people have sudden shifts in preferences. I could not have anticipated, for example, the ‘sweatpandemic’ we have been going through.” She added that being comfortable with change is an important aspect of the stylist mindset.

Even for a data scientist, Maskalevich says the stylist job can be quite intellectually demanding; “You can’t get in a rut,” she said. The most important part of the job is establishing and maintaining the connection with each individual client. She has been working with one client for five years; her client has shared vacation photos and they have shared life moments over Fix request notes and styling notes. Maskalevich gives considerable thought to what items she’s going to send the client next. “That really makes the job engaging,” she commented.

Caitlin Yacopetti, A Styling Supervisor

Caitlin Yacopetti is a Styling Supervisor at Stitch Fix with over six years of experience supporting a team of stylists to deliver great experiences for clients. She said that the styling at the company is a blend of art and science. The science, of course, is the algorithm-based recommendations that help them make informed decisions on what they send to the client in the Fix, whether that’s recommending items based on their style preferences or making suggestions for clothes that will fit them best. Yacopetti said that stylists also get a really good understanding of clients when they sign up for Stitch Fix—where they live, their lifestyle and fit challenges—without ever meeting them.

She also described the art component of the job:

She feels that the algorithms give stylists the ability to make better and more efficient choices—”They help to remove our own personal style biases so that we don’t get distracted by the item that might catch our eye that matches our own personal taste, and instead focus on the items that are right for the client, which is of course the most important thing. The algorithms also provide the efficiencies that enable personalization at scale. For example, taking out pink if a client has told us they don’t like the color on them, or homing in on the pair of jeans that we know will fit just right, are both huge time savers.

Yacopetti says that in the day to day work of styling there is no need to know anything technical about the algorithms, but it’s important that all stylists understand the context of algorithms in the styling process and so trust the algorithm and its recommendations.

When asked how she saw the stylist role evolving in the future, she commented: “We have more than 5,000 expert stylists who have built the trusted relationships we know our clients value and enjoy. We see a huge opportunity to deepen that human connection a stylist can provide, whether through offering live video calls with stylists or through regular style tips in the Stitch Fix app.”

Human stylists are an integral part of the Stitch Fix business model, and it seems unlikely that the need for both client/stylist relationships and interpretation of unusual client comments will be satisfied by artificial intelligence. Thus there seems to be little likelihood that clothing stylists will be fully automated anytime soon. In the meantime, Stitch Fix will further optimize its blend of art and science in the service of its clients buying and wearing stylish clothes.

I’m the President’s Distinguished Professor of IT and Management of Babson College, a Digital Fellow at the MIT Initiative on the Digital Economy, and a Senior Advisor to

推荐文章