Are Clothing Algorithms the Future of the Apparel World?
With Amazon revolutionizing the apparel world regularly, it looks like other online retailers are looking to prove their expertise, as well. Subscription startup Stitch Fix has figured out a new way to keep clothes flying off the shelves, and it's all about data science, according to Quartz.
The fashion brand employs a data science team that predicts what consumers want. The team looks at areas for growth by analyzing gaps in the company's inventory.
“If we could be accurate enough to buy and hold inventory, could we be accurate in what isn’t available to buy, what doesn’t exist?” Eric Colson, chief algorithm officer for Stitch Fix, asked. “Now when something is ostensibly missing from the market, we fill it in with our own algorithmically generated designs.”
But, of course, it's a little more technical than that. Here's the breakdown:
Three initial algorithms create a starting point. The first algorithm picks three recommended pieces of clothing that could be combined or used as a template for a new piece. The second algorithm picks three different attributes that have been shown to compliment the initial designs' attributes. The third algorithm suggests an attribute not previously suggested. Then, these suggested attributes analyze trillions of potential combinations to come up with nine suggestions.
From there, its's on the humans to put these suggestions into action to create new garments. It's a team effort.
It seems whatever Stitch Fix is doing is working. The company has already brought in $500 million in revenue, and some of the new designs have performed in the 99th percentile for the site's inventory.
It will be interesting to see if this analytics-driven design force will become the new normal in the future.
Hannah Abrams is the senior content editor for Promo Marketing. In her free time, she enjoys coming up with excuses to avoid exercise, visiting her hometown in Los Angeles and rallying for Leonardo DiCaprio to win his
first second Academy Award.