Their model uses a wide variety of data, according to Sam’s Club officials. Things like local temperatures (warm weather often means fewer pies purchased); whether Sunday’s football game is home or away (home games may mean more pies are needed); how popular pecan pies are this year (more pecan pies can mean less pumpkin pie sales).
These data points, and others, connect to an artificial intelligence model they created. He spits out recommendations to each store manager, such as how many pies should be available in their stores per hour. Last year, Sam’s Club sold enough pumpkin pies to fill up 450 soccer fields, officials said. (They declined to give an exact figure.)
Forecasting demand accurately is necessary, officials added, because competition to retain customers is fierce and profit margins are tight.
“If members don’t get what they need, they won’t renew their contract with us,” said Pete Rowe, vice president of technology at Sam’s Club and member of the store whose family both buy a pumpkin pecan pie for Thanksgiving this year. “It’s critical for us and our model to make sure of that.”
In recent years, sophisticated artificial intelligence models have become commonplace in grocery stores. Spurred by the pandemic and supply chain challenges, it’s rapidly changing the grocery shopping experience: from AI-powered shopping carts that automatically recognize items you’ve picked up to chef robots that generate revenue based on your purchases.
The rise is due to a confluence of factors, according to grocery experts. Stores now have access to mountains of data, including third-party brokers and shopper loyalty programs. Computer processing power is cheaper and faster. Machine learning models, software that computers use to learn and adapt on their own, have evolved. The pandemic has played a big role.
Gary Hawkins, chief executive of the Center for Retail and Technology, said that in the pre-pandemic era, stores used software to help with inventory management, staffing and forecasting when goods will be in stock. But after the pandemic hit, “supply chains exploded, demand exploded” and grocery stores were unprepared and needed smarter systems, Hawkins said.
“It literally blew up all the models, because they just weren’t sophisticated enough,” he added. “So very quickly, especially the big guys said, ‘We need something better here.’ ”
In April 2019, Walmart launched a Intelligence Research Lab where cameras and sensors are connected to algorithms to monitor the level of shelf storage. In March, Kroger launched an AI lab where technology can track the freshness of vegetables. ketchup maker Kraft-Heinz now uses machine learning to track demand for its products ahead of events like the Super Bowl. Amazon opened a fully automated Whole Foods this year that uses deep learning software to allow customers to shop and check out without the need for a cashier. (Amazon founder Jeff Bezos owns The Washington Post).
Start-ups have also multiplied. Based in New York caper cart makes AI-powered shopping carts that automatically recognize what customers pick up and check out. from Seattle shelf engine tells stores how many items they need daily. Winterbased in Australia, has a model to advise grocers on where to put products on the shelves.
“AI is making its way into almost every technology-related capability,” Hawkins said.
Dominic D’Agostino, a 30-year-old member of Sam’s Club in Dayton, Ohio, said he had no idea the company used such sophisticated technology to predict pumpkin pie demand.
Although he’s not a fan of the dish and probably won’t bring it to his sister’s house for the holidays – “the only pie I really like is pizza,” he said. says – D’Agostino is intrigued and somewhat worried, that artificial intelligence is being used in this way.
“It’s scary,” he said in an interview. “It’s also fascinating.”
Sam’s Club made the decision to use AI shortly before the pandemic hit, Rowe said. The channel used software to guide its operations, but felt it could be better.
In years past, for example, Rowe said, “We were making too many pumpkin pies, too many croissants and that [would lead] to our associates who waste their time and to us who have to throw away inventory.
Now the company uses machine learning to forecast inventory for everything it makes in-house, like pies and roast chicken. They also have “autonomous floor scrubbers” — or autonomous robots — to scan shelves and send alerts to staff prioritizing which items need to be replenished first when delivery trucks arrive.
Rowe said it helped the store become more than 90% accurate in forecasting demand and wanted it to be higher.
Despite the appeal of AI, it comes with risks. Algorithms mine troves of customer data, fueling privacy risks, researchers from the University of Arkansas said. It can also lead to bias.
“Even if race or gender is not a formal input to an AI algorithm,” they wrote, “an AI application can impute race/gender from other data and use to “increase the price” for specific demographics.
Others note that AI isn’t a one-size-fits-all solution and stores could be wasting money buying fancy software just to keep up with the hype.
“You can’t be too in love with the shiny object element of AI,” said Mike Hanrahan, former general manager of Walmart’s Intelligence Research Lab. said in a technical publication. “There are a lot of shiny objects that do things that we think are unrealistic at scale and probably, in the long run, not beneficial to the consumer.”