Their model uses a wide variety of data, according to Sam’s Club officials. Things like local temperatures (hotter often means fewer cakes purchased); whether the Sunday football match is home or away (home games can mean more pies are needed); how popular are pecan pies this year (more pecan pies can translate into less pumpkin pie sales).
Those data points, and others, connect to an AI model they created. Spit out tips to each shop manager, such as how many cakes should be available in their shops each hour. Last year, Sam’s Club sold enough pumpkin pies to fill 450 football fields, officials said. (They declined to give an exact figure.)
Forecasting demand with specificity is necessary, the 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 with us,” said Pete Rowe, vice president of technology at Sam’s Club and shop member whose family is buying both pumpkin and pecan pie for the Thanksgiving quest. ‘year. “It’s crucial for us and for our model to be sure of that.”
Pumpkin pie or pecan pie? With these recipes, you don’t have to choose.
In recent years, sophisticated AI models have become commonplace in grocery stores. Spurred by the pandemic and supply chain challenges, the grocery shopping experience is rapidly changing: from AI-powered shopping carts that automatically recognize the items you’ve picked up to robot chefs that generate recipes based on your shopping.
The increase is due to a confluence of factors, according to food experts. Stores now have access to mountains of data, including from third-party brokers and buyer loyalty programs. Computer processing power is cheaper and faster. Machine learning models, software that computers use to learn and adapt on their own, are advanced. The pandemic has played a big role.
Gary Hawkins, chief executive officer of the Center for Retail and Technology, said in pre-pandemic times stores used software to help with inventory management, staffing and predicting when goods would be available. But after the pandemic, “supply chains blew up, demand skyrocketed,” and grocery stores were unprepared and needed smarter systems, Hawkins said.
“He literally blew up all the models, because they just weren’t sophisticated enough,” she added. “So very quickly, mostly the bigwigs said, ‘We need something better here.’ “
In April of 2019, Walmart launched an intelligence research lab where cameras and sensors are linked to algorithms to monitor how stocked shelves are. In March, Kroger launched an AI lab where the technology can track the freshness of vegetables. Ketchup maker Kraft Heinz is now using machine learning to track demand for its products ahead of events like the Super Bowl. This year, Amazon opened a fully automated Whole Foods that uses deep learning software to allow customers to shop and walk out without the need for a cashier. (Amazon founder Jeff Bezos owns the Washington Post).
Startups have also proliferated. New York-based Caper Cart makes AI-powered shopping carts that automatically recognize what customers pick up and check them out. Seattle’s Shelf Engine tells stores how many items it needs each day. Australia-based Hivery has a model for advising grocers on where to put products on shelves.
“AI is making its way into almost every technology-related capability,” Hawkins said.
This World Cup is wired and powered by artificial intelligence
Dominic D’Agostino, a 30-year-old Sam’s Club member in Dayton, Ohio, said he had no idea the company used such sophisticated technology to predict demand for pumpkin pie.
While he’s not a fan of the dish, and probably won’t be bringing any to his sister’s house for the holidays — “the only pie I really like is pizza,” he said — D’Agostino is intrigued and a little worried , that artificial intelligence is used in this way.
“It’s creepy,” she said in an interview. “It’s also charming.”
Sam’s Club made the decision to use AI just before the pandemic hit, Rowe said. The chain has used the software to drive its operations, but felt it could be better.
In past years, for example, Rowe said: “We made too many pumpkin pies, too many croissants and so on [would lead] to our collaborators who waste time and also to us who have to throw away the inventory.
Now, the company uses machine learning to predict inventory for everything it produces in-house, like pies and rotisserie chicken. They also have “autonomous scrubber dryers” — or self-driving robots — to scan shelves and send alerts to staff prioritizing which items need to be replenished first when delivery trucks arrive.
Rowe said it has helped the store become 90% more accurate in forecasting demand and wants it to be higher.
The Google engineer who thinks the company’s AI has come to life
Despite the allure of AI, it has risks. Algorithms exploit customer data, fueling privacy risks, said researchers at the University of Arkansas. It can also lead to bias.
“Even if race or gender is not a formal input into an AI algorithm,” they wrote, “an AI application can impute race/gender from other data and use that to ‘price higher’ a data specific demographics”.
Others note that AI isn’t a one-size-fits-all solution, and stores may be wasting money buying fancy software just to keep up with the hype.
“You can’t be overly enamored with the shiny object element of AI,” Mike Hanrahan, former managing director of Walmart’s Intelligence Research Lab, said in a technology publication. “There are a lot of shiny objects out there that are doing things that we think are unrealistic to scale and probably, in the long run, not beneficial to the consumer.”