Walmart combats grocery out-of-stocks with AI

Dan Berthiaume
Senior Editor, Technology
Dan Berthiaume profile picture

As surging online demand for food and groceries affects inventory levels, Walmart is using artificial intelligence (AI) to ensure optimal substitutions.

During the COVID-19 pandemic in 2020, Walmart customer behavior shifted radically. Customers increasingly began shopping online for everyday needs, including food and groceries. That surge in demand presented a challenge to Walmart, as the combination of in-store shoppers and online volume meant some popular items could quickly sell out. 

In response, Walmart began leveraging proprietary artificial intelligence (AI) technology to help both customers and personal shoppers choose the best substitute for an out-of-stock item. Each individual customer has unique substitution preferences and needs, and a wrong substitution choice can negatively impact customer satisfaction and increase costs. 

Previously, Walmart personal shoppers would go through a manual process to determine the best way to manage a substitution. But there are nearly 100 different factors that can go into that decision, meaning personal shoppers could not realistically manage all the variables while manually filling online grocery orders.

To help ensure substitutions that satisfy individual customers, Walmart developed a deep learning AI technology solution to help identify the next best item for customers if an item they selected is out of stock. The solution considers hundreds of variables, such as size, type, brand, price, aggregate shopper data, individual customer preference, and current inventory, in real-time to determine the best next available item. 

The solution then pre-emptively asks the customer to approve the substituted item or let Walmart know they don’t want it. That signal is then fed back into Walmart’s learning algorithms to improve the accuracy of future recommendations. Following the deployment of this technology, Walmart says customer acceptance of substitutions has increased to over 95%. 

If a personal shopper is preparing orders and come across an item that is not available, the system suggests the alternative product, and shows the personal shopper where the item is located in the store, simplifying the decision-making process and streamlining order fulfillment. 

“We continue to iterate and enhance this technology, and our customers are responding positively,” said Srini Venkatesan, executive VP, Walmart Global Tech, in a corporate blog post. “The best part is, throughout the entire process the system is learning and getting smarter based on customer input and actions. Our goal is never to be out of stock and never to have substitutions. But, when it happens, the technology we’ve built helps ensure customers get the next best thing.”