McDonald’s Uses Machine Learning to Modernize its Menus

McDonald’s is buying Dynamic Yield, an Israeli startup decision-logic technology company, for $300+ million with the aim of better personalizing its menus. The technology will let restaurants vary their electronic menu displays depending on the weather, time of day or regional preferences — and suggest meal add-ons. McDonald’s serves about 68 million customers every day, the majority of whom use the drive-thru window. Chief executive Steve Easterbrook has pushed technology to drive sales and lift the company’s profile.

Bloomberg reports that McDonald’s shares “rose as much as 1.7 percent to $188.88, the highest in two months, on Tuesday … [and] the stock has gained almost 6 percent this year.” Baird analyst David Tarantino stated that the deal could “be slightly dilutive in the early stages,” but ultimately help McDonald’s grow and “elevate the customer experience.”

McDonald’s tested Dynamic Yield’s technology in 2018 in the U.S. and will roll it out more widely “this year for drive-thru menus once the deal closes.” McDonald’s will then be Dynamic Yield’s sole owner; it plans to continue to invest in the company, which will remain standalone. Its customers have included HelloFresh, IKEA and Urban Outfitters.

Wired reports that the deal is the fast food chain’s biggest since it bought Boston Market 20 years ago. In 2018, McDonald’s “tallied nearly $6 billion of net income, and ended the year with a free cash flow of $4.2 billion.” Easterbrook’s digital strategy has thus far included debuting an app and partnering with Uber Eats, “in addition to making a number of infrastructural improvements.”

“What we hadn’t done is begun to connect the technology together, and get the various pieces talking to each other,” said Easterbrook. “How do you transition from mass marketing to mass personalization? To do that, you’ve really got to unlock the data within that ecosystem in a way that’s useful to a customer.”

The company’s pilot program in Miami used Dynamic Yield to “crunch data as diverse as the weather, time of day, local traffic, nearby events, and of course historical sales data, both at that specific franchise and around the world.” “We’ve never had an issue in this business with a lack of data,” said Easterbrook. “It’s drawing the insight and the intelligence out of it.”

McDonald’s wouldn’t share any “specific insights” but Wired proposes that “as with any machine-learning system, the real benefits will likely come from the unexpected.” McDonald’s executive vice president/global chief information officer Daniel Henry noted that “when you look at the answers that this decision engine provides, it may not seem so obvious to begin with, but for customers it makes sense.”

“It’s not just about the individual, it’s also taking training information from other customers,” he added.

By gathering so much data, said Easterbrook, “ultimately you can see we’ll be able to use predictive analytics.” “We’re going to have real-time information, as we start to connect the kitchen together — further back through our supply chain,” he explained. “As you start to link the predictive nature of customer demand all the way through your stock levels in the restaurant and the kitchen, you can almost flex it back down through the supply chain.”