BoF Logo

The Business of Fashion

Agenda-setting intelligence, analysis and advice for the global fashion community.

The New Way Brands Are Battling, and Sometimes Even Beating, Bots

Rather than limit who can put in orders for limited-edition sneakers, watches and collectibles, retailers are throwing open their drops — and then using data analytics to quietly kick bad actors to the back of the line.
The EQL launch page for the Joe Freshgoods x New Balance "Keisha Blue"
Joe Freshgoods x New Balance 990v4 in "Keisha Blue." (EQL)

Key insights

  • The spread of the drop model from sneakers and streetwear to categories like luxury has created the need for more reliable methods of filtering out bots and bad actors.
  • While big players like Nike have built their own defences, others have turned to external tech providers like the Australian start-up EQL, which has emerged as a leader in managing fashion and footwear releases.
  • Businesses are trying to reassure customers they're doing all they can to make launches fair, including prioritising shoppers who missed out on previous releases.

The launch of New Balance’s latest collaboration with Joe Freshgoods last month was destined to be a target for bad actors looking to flip the shoes on the resale market.

The Chicago designer and creative director is behind some of New Balance’s most coveted sneaker releases of the past few years. With limited quantities available, his “1998″ collection of three versions of the brand’s 990v4 model was sure to be irresistible to buyers using automated bots or multiple accounts to snatch up as many pairs as possible, leaving ordinary shoppers empty-handed or forced to pay a premium once resellers listed the shoes online.

Freshgoods had tried different methods designed to get his sneakers into the hands of fans, including a release through Instagram Shop. But running a drop that filtered out resellers without creating problems for regular buyers had proved difficult.

For the “1998″ drop, he teamed with EQL, an Australia-based start-up founded by three ex-Google employees that has quickly become a popular line of defence for retailers looking to protect their product releases from bots and bad actors.

Since launching in 2021, EQL — pronounced “equal” — has run sneaker drops for retailers such as Atmos and A Ma Maniére and expanded into industries from luxury goods to art and collectibles, including managing Tiffany’s sale of a line of Pokémon-themed jewellery this past November.

Its rapid rise is the latest example of the escalating arms race between retailers and resellers. Bots have become a nuisance in the release of just about any hyped product that can be resold at a markup, whether it’s sneakers, gaming consoles, concert tickets, toys or watches. Nike, a constant target of bot attacks, has said they can account for as much as 50 percent of raffle entries for some releases on its SNKRS app. US lawmakers have even proposed outlawing bots. The legislation has never moved forward, but in what’s become something of a holiday tradition, Rep. Paul Tonko, a Democratic congressman from New York, reintroduced his “Grinch bot” bill in December.

“A lot of consumers don’t understand how hard it is to release sneakers,” Freshgoods said. “As technology on stopping bots continues to rise, the people that control the bots and all that stuff, they get wiser too.”

Big players like Nike have built their own defences. Those short on resources or technical expertise can turn to outside providers like EQL, which has emerged as a leader for footwear and fashion releases. To date, it has run more than 4,000 launches in 15 markets for brands and retailers from Crocs and Foot Locker to Bulgari and Tiffany, including the jeweller’s Nike Air Force 1 drop.

It’s hard to say exactly how effective the various anti-bot measures employed by retailers are proving. Companies don’t often publicise their release quantities, or the share snatched up by bots. Consumers may also blame bots for missing out on an item when the reality is there was just far more demand than supply available. But with resellers continuing to snatch up inventory — and posting pictures online of rooms full of items that were supposed to be protected from bots — many consumers want to see retailers doing more.

“There are clear signs that brands are thinking about this stuff, and they’re a little bit better about it,” said Mike Sykes, who writes the sneakers and business newsletter The Kicks You Wear. “But still there are times where it just seems like resellers are able to slip through the cracks and scoop up crazy amounts of these sneakers. It’s definitely frustrating for people.”

Battling the Bots

The basic strategy for battling bots in the past was to separate the computer programs from the humans and block them before they could enter a draw. CAPTCHA tests were an early tactic. But with advancements in machine learning and computer vision, bots are now faster and better than humans at identifying objects or distorted letters, according to a 2023 study.

Rather than try to put up a wall that bots can’t scale, EQL, which patches into e-commerce platforms like Shopify and Salesforce Commerce Cloud or can host sales through its own web domain, uses security methods that are invisible to shoppers and resellers alike.

While any user can submit an entry through its raffle system, EQL analyses hundreds of thousands of signals to evaluate and score users based on their characteristics and activity, including across different launches, much like a bank evaluating a customer’s qualifications for a loan, according to Andrew Lipp, EQL’s co-founder and chief executive. It looks at unique fingerprints like IP address and browser details, as well as examining user groups and behaviour to determine the likelihood that someone submitting an entry is a real person or a reseller’s bot.

It runs live-learning models, too, that assess ground data. If the volume of users in a zip code seems off, for instance, the models will search for other signals that indicate whether something nefarious is going on. One obvious attempt to game the Joe Freshgoods raffle came from a user who submitted 40 entries with the same name and address.

“The thing that we do that’s quite different is we let everyone in,” Lipp said. “If you’re a bad actor, a scammer, someone dodgy, you still think you’ve come through our platform. You won’t know if you’re being clipped.”

The platform is able to give preference to groups like loyal customers or locals. That was an important point for Freshgoods, who wanted to reward his fellow Chicagoans by releasing one colourway from the drop, the “Keisha Blue,” only for local pickup in the city.

The users EQL determines to be following the rules get ranked higher. EQL awards wins to the “best” users first and works its way down the list, automatically processing payments and allocating the inventory that the retailer has put into the system. Towards the end of the Joe Freshgoods raffle, EQL found three percent of entries coming from bots and bad actors, while nine percent showed signals that could impact their chance of winning.

On the Monday the Joe Freshgoods raffle went live, sneakerhead Adham Abousalem joined the draw for two of the styles. He signed into EQL, put in his personal information and submitted the size he wanted. Then he waited. When the draw closed on Friday, he won one of the styles he tried for, the predominantly black “Outro.” EQL automatically charged his card and processed the order for Joe Freshgoods to fulfill. It was no different than other raffles he’d entered over the years, he said.

“Now, talking from the back end, I believe there’s something behind the scenes going on,” Abousalem said. “In terms of the bot community, a lot of the bots that were used for raffles have given up entirely on EQL, saying that they filter very hard.”

The Art of the Drop

The spread of the drop model means more companies need strategies for dealing with people looking to game the system. Lipp also pointed out that, as luxury businesses look to reach younger audiences with these collaborations, they’re appealing to more shoppers accustomed to drops. A bad launch, however, can potentially tarnish the experience a brand tries to create with the design and storytelling around its products and undermine consumer trust, as many sneaker sellers know all too well.

In April 2022, for example, the sneaker and streetwear retailer Union Los Angeles apologised to customers for the bot protection on its Jordan 2 launch being “a bit too good” after many genuine shoppers were left unable to check out, leading to complaints online.

The problem isn’t just bots. Often there’s far more demand than inventory. EQL calculates a “hype score” on each drop, calculated as total number of inventory available divided by number of entries. One day into the Joe Freshgoods launch, the “Keisha Blue” colourway in size 14 for in-store pickup had 28 times more entries than there was inventory available.

“You will see a lot on social media of people saying they hate EQL because they never win,” Abousalem said.

Sykes of The Kicks You Wear pointed out that many shoppers are feeling fatigued with all the bots, competition and stories of retailers doing backdoor sales. They want more transparency from brands about the quantities available, and really just to know that things are being handled fairly. The whole situation is arguably contributing to a softening of sneaker resale prices.

Businesses are trying to reassure customers they’re doing what they can. Nike, for one, has responded by running drops that prioritise shoppers who’ve lost previous raffles. EQL has introduced what it calls the EQLizer Score: every raffle a user fairly enters and loses increases their chances of winning at that retailer next time.

“The raffle system works for us because it just makes it fair,” Freshgoods said. “What I deem a proper drop is sell-through and if people that have been supporting me can get it and new people can get it — and just fairness. I want to see real people wearing them.”

Further Reading

An online economy of tips, proxy servers and automated applications has grown out of the hype-driven sneaker market, and the rise of the casual reseller is only making it harder to shop for the latest releases.

About the author
Marc Bain
Marc Bain

Marc Bain is Technology Correspondent at The Business of Fashion. He is based in New York and drives BoF’s coverage of technology and innovation, from start-ups to Big Tech.

In This Article

© 2024 The Business of Fashion. All rights reserved. For more information read our Terms & Conditions

More from Technology
Analysis and advice on how technology is disrupting fashion and creating new opportunities.

The social-media giant is making it easier for users to find inspirational images of people with similar hair, skin and body types as them, helping it attract Gen-Z consumers who are using shopping features on the platform at a higher rate than any other group.

US consumer spending across online luxury sellers like Farfetch, Matches and Net-a-Porter suffered sustained declines throughout 2023. The question is whether the downturn is simply temporary or the luxury e-commerce model itself is broken.

view more

Subscribe to the BoF Daily Digest

The essential daily round-up of fashion news, analysis, and breaking news alerts.

The Business of Fashion

Agenda-setting intelligence, analysis and advice for the global fashion community.
BoF Professional Summit - New Frontiers: AI, Digital Culture and Virtual Worlds - March 22, 2024
© 2024 The Business of Fashion. All rights reserved. For more information read our Terms & Conditions, Privacy Policy, Cookie Policy and Accessibility Statement.
BoF Professional Summit - New Frontiers: AI, Digital Culture and Virtual Worlds - March 22, 2024