“A key tenet of our personalization model is that the more information clients share, the better we are able to personalize their recommendations. We are usually able to adapt the model based on feedback from our clients; however, rules-based systems aren’t generally adaptive. We need the system to learn from client feedback on the outfits it recommends. We’re receiving immensely helpful feedback, from how clients engage with the outfit recommendations and also from a custom-built internal QA system.
Style Profile: When a client signs up for Stitch Fix, we receive 90 different data points — from style to price point to size.
Feedback at checkout: 85% of our clients tell us why they are keeping or returning an item. This is incredibly rich data, including details on fit and style — no other retailer gets this level of feedback.
Style Shuffle: an interactive feature within our app and on our website where clients can “thumbs up” or “thumbs down” an image of an item or an outfit. They can do this at any time — so not just when they receive a Fix. So far, we’ve received an incredible 4 billion item ratings from clients. Personalized request notes to Stylists: Clients give their Stylists specific requests, such as if they are looking for an outfit for an event, or if they’ve seen an item that they really like.”
“Data science isn’t woven into our culture; it is our culture. We started with it at the heart of the business, rather than adding it to a traditional organizational structure, and built the company’s algorithms around our clients and their needs. We employ more than 80 data scientists, the majority of whom have PhDs in quantitative fields such as math, neuroscience, statistics, and astrophysics. Data science reports directly to me, and Stitch Fix wouldn’t exist without data science. It’s that simple.”
“Who do you turn to when you can’t decide what to wear? Your best friend, maybe. Instagram, probably. Fashion magazines, maybe. But soon, perhaps, it will be none of the above. Instead, you will try on an outfit, turn to a wall-mounted, five megapixel camera with front lighting and dual-antennae WiFi connectivity, and ask: “Alexa, how do I look?” and within a few seconds the 1.6 watt speaker will deliver the data-driven, empirically-founded assessment.
The metric of a style algorithm that is based on likes, whether fed to you as feedback on your selfies or as a subscription box of suggested seasonal choice of clothes, will steer you towards a polished, palatable, mainstream look. “If the algorithm is based on mass approval, it is not going to propose you wear a weird top with one sleeve,” says Alistair O’Neill, professor of fashion at Central St Martins.
Stitch Fix: This is a online personal styling service, primarily available to clients in the United States, which sends its 2.7 million active American clients ‘suggestion boxes’ of clothes chosen by cross-referencing a client’s stated preferences with the recent purchases of others of similar age and demographic.
They could be programmed to surprise. Brad Klingenberg, vice-president of Stitch Fix, states that the aim is to “delight” clients, rather than just please them, suggesting an element of the unexpected.
But maybe the truth also is, we are more like the robots than we’d like to think. “The majority of people have already developed an algorithm for style, even if they don’t think of it like that,” says Simon Lock, founder and CEO of Ordre, which offers fashion buyers a digital, streamlined alternative to physical showrooms. “For instance, I wear black and white, a slim fit silhouette, always Thom Browne brogues. Essentially, the eye captures a look and the brain informs the wearer whether you like it or not based on history and personal taste. Artificial intelligence is perfectly suited to perform this role for us.”
“Online shopping, as we know it, is a lousy experience, because you are essentially looking at an inventory. One day in the future you will be sitting on your sofa next to a virtual Diana Vreeland, or Alexa Chung, who will be talking you through the selection of virtual clothes,” she says.
Retailers are already experimenting with incorporating data from your calendar — about a future trip, and what the weather forecast is for that location, for instance — into what gets served up as cookies. Artificial intelligence could sprinkle fairy dust on the online shopping experience, so that instead of scrolling through a hundred skirts, you are matched with one you fall in love with. “The entire industry is focused right now on what the consumer-facing aspect of AI in retail will be. It has to be something meaningful.”
“I think it’s inevitable that pretty soon we will each be represented in the digital sphere by an avatar,” Hackford says. ‘It will compare available prices on everything you want to buy. It will sit in the hold queue on the phone to buy a train ticket. It will do all the things that technology does better than you can and allow you more time for being human.”