Walmart uses AI to predict how much Thanksgiving pumpkin pie will sell

Make a comment

Turkey gets everyone’s attention. Cranberry sauce ruffles feathers. But pumpkin pie is a favorite staple that many Americans crave at Thanksgiving.

And many don’t want to make it themselves. That’s why Sam’s Club, the Walmart-owned retail and grocery warehouse, is using artificial intelligence to estimate how many pies each of its nearly 600 stores should make for the holidays.

According to Sam’s Club officials, their model uses a wide variety of data. things like local temperature (warmer weather often means buying less pie); whether the Sunday football game is home or away (home games may require additional pies); How popular are pecan pies this year (more pecan pies may translate into fewer pumpkin pie sales).

Plug those data points, and others, into the artificial intelligence model they build. It spits out recommendations to each store leader, such as how many pies their stores should have on hand in an hour. Last year, Sam’s Club sold enough pumpkin pie to fill 450 football fields, officials said. (They declined to give an exact figure.)

Forecasting demand with specificity is essential, officials added, because competition to keep customers is cutthroat and profit margins are tight.

“If members don’t get what they need, they don’t renew with us,” said Pete Rowe, Sam’s Club vice president of technology and store member whose family is buying both pumpkin and pecan pie for Thanksgiving this year. “It’s important for us and our model to ensure that.”

Also Read :  Elon Musk cuts Twitter’s cloud infrastructure budget

Pumpkin pie or pecan pie? With these recipes, you don’t need to choose.

In recent years, sophisticated artificial intelligence models have become commonplace in grocery stores. Inspired by the pandemic and supply-chain challenges, it’s rapidly changing the grocery shopping experience: AI-powered shopping carts that automatically generate recipes based on your purchases to chef bots that recognize the items you’ve picked up.

According to grocery experts, the increase is due to a confluence of factors. Stores now have access to mountains of data, including third-party brokers and shopper loyalty programs. Computer processing power is cheap and fast. Machine learning models, the software that computers use to learn and adapt to themselves, have advanced. Epidemics have played a big role.

Gary Hawkins, chief executive of the Center for Retail and Technology, said that before the pandemic, stores used software to help manage inventory, staff and predict when goods would be in stock. But after the pandemic hit, “supply chains blew up, demand went through the roof” and grocers were unprepared and needed smarter systems, Hawkins said.

“It literally blew up all the models, because they weren’t sophisticated enough,” he added. “So early on, especially the big guys said: ‘We need something better here.’ “

In April of 2019, Walmart launched an intelligence research lab where cameras and sensors are wired into algorithms to monitor how well-stocked shelves are. In March, Kroger launched an AI lab where technology can keep track of the freshness of vegetables. Ketchup maker Kraft Heinz now uses machine learning to track demand for its products leading up to events like the Super Bowl. Amazon opened a fully automated Whole Foods this year that uses deep-learning software to let customers shop and check out without the need for a cashier. (Amazon founder Jeff Bezos owns the Washington Post).

Also Read :  Internet ‘obsessed’ with new Princess of Wales pics as one detail sparks plea

Start-ups have also grown. New York-based Caper Cart makes AI-fueled shopping carts that automatically track what customers pick up and check them out. Seattle’s Shelf Engine tells stores how many items they need daily. Australia-based Hivery has a model that advises grocers on where to stock items.

“AI is entering almost every technology-related capability,” Hawkins said.

This World Cup is wired and fueled by AI

Dominic D’Agostino, a 30-year-old member of Sam’s Club in Dayton, Ohio, said he had never known the company used such sophisticated technology to predict demand for pumpkin pie.

Although he’s not a fan of the dish, and probably won’t bring any to his sister’s house for the holidays — “The only pie I really like is pizza,” he said — D’Agostino is curious, and somewhat worried, about how artificial intelligence is being used.

“It’s scary,” he said in an interview. “It’s adorable too.”

Sam’s Club decided to use AI shortly before the pandemic, Rowe said. The chain used software to guide its operations, but it could be better.

In past years, for example, Rowe said “we’ll produce more pumpkin pies, more croissants. [would lead] Our associates should waste their time and throw us the list.

Also Read :  Arizona high school students learn about A.I. and related career paths

Now, the company uses machine learning to predict inventory for everything it makes in-house, like pies and rotisserie chicken. They have “autonomous floor scrubbers” — or even self-driving robots — to scan shelves and send alerts to employees prioritizing which items need to be restocked first when delivery trucks arrive.

Rowe said this has helped the store be more than 90 percent accurate at predicting demand, and wants it to be higher.

A Google engineer who thinks the company’s AI has come to life

Despite AI’s appeal, it has risks. Algorithms close tracks of customer data, raising privacy risks, University of Arkansas researchers said. It can also lead to bias.

“Although race or gender is not a formal input to an AI algorithm,” they wrote, “an AI application can infer race/gender from other data and use it to ‘value higher’ a specific demographic.”

Others note that AI is not a universal solution, and that stores may waste money buying fancy software to keep up the hype.

“You can’t get too enamored with the shiny object element of AI,” said Mike Hanrahan, former chief executive of Walmart’s Intelligence Research Lab, in a technical publication. “There are a lot of shiny objects that are doing things that we think are unrealistic to scale and probably, in the long term, are not beneficial to the consumer.”


Leave a Reply

Your email address will not be published.

Related Articles

Back to top button