Edge Computing Helps Power Taco Bell’s Digital Business

At Taco Bell, a computer server at each location ingests data from in-person and digital orders and customer loyalty accounts, as well as kitchen operations, and uses custom algorithms to make decisions about, for example, when to say fryer employees to sink the potatoes for a Nacho Fries order so they are hot when a delivery driver arrives for pickup, Mr Parizher said.

“We have taken [on] our most critical workloads in order processing and menu data,” said Parizher. “If he makes it work more efficiently than you had before, even by a small percentage, for a Fortune 500 company, the results are significant.”

The so-called edge is not a place but a computing model, said Lynda Stadtmueller, senior vice president of information and communications technology practice at Frost & Sullivan, a market research firm .

Key aspects are detection devices, connectivity, analysis and responsiveness, said Ms Stadtmueller, speaking at the same event.

The goal is to improve application performance by processing data where it is generated, such as in a local Taco Bell, and applying it at lightning speed. Energy companies, retailers and industrial manufacturers are using edge computing to take advantage of fast internet speeds, including 5G networks, and a growing range of connected devices. General Electric Co.

and Siemens AG

for example, use edge computing to optimize factory machinery in real time.

“A John Deere tractor is an advantage when equipped with sensors that may be monitoring components. Your phone could be an advantage when it collects data or a kiosk contacts and contacts it,” Ms Stadtmueller said.

Taco Bell spent about five years building state-of-the-art computing capabilities, Parizher said. Each location has duplicate devices to act as backup in case of failure.

In addition to entering a storefront or using a drive-thru, Taco Bell consumers can order their Mexican pizzas and Chalupa Supremes through the company’s website, mobile app, food delivery services and, in some geographies, via text messages. In January, the channel rolled out a nationwide subscription service. For $10, customers can purchase a Taco Lover’s Pass to get one taco a day for 30 days. The menus are personalized according to the place.

When a regular customer places an order, the local restaurant’s system retrieves the relevant information from the cloud. Understanding frequent purchases, typical order sizes and a penchant for trying on specialty items helps determine whether to offer a personalized offer, Parizher said.

In addition to processing and analyzing orders from a multitude of platforms, restaurants must manage menu adjustments, food assembly and staffing changes, as well as data from multiple channels at once, Mr. Parizher said. “You process these events and try to optimize them. We’re no different from manufacturing, in a way,” he said.

The team had to think about how to protect customers’ personal data within the Taco Bell loyalty program. “For security reasons, we don’t want this information to be in the store,” he said, so it’s stored in the cloud. “You don’t keep data at the edge longer than necessary.”

Taco Bell contracted with a third party for a platform to monitor global edge computing activity while Mr. Parizher’s own team built the software to route order data to various connected devices in kitchens, he said.

With the basics of edge computing in place, he said, Taco Bell can experiment with connected robotic equipment capable of frying food, warming tortillas or pouring drinks. “Now it gets a little more exciting,” he said.

Write to Kim S. Nash at kim.nash@wsj.com