News
3/30/2015
08:06 AM
Connect Directly
Google+
LinkedIn
Twitter
RSS
E-Mail

Microsoft Azure Services Power Ziosk Dining Experience

Microsoft HDInsight and Azure ML help Ziosk gain dining insights from more than 77,000 table-top tablets deployed at Chili's and other restaurants.



Windows At 30: Microsoft's OS Keeps Evolving
Windows At 30: Microsoft's OS Keeps Evolving
(Click image for larger view and slideshow.)

Casual restaurant chains want to attract digitally savvy millennials more than any other segment of diners. They're trying social network campaigns and mobile apps to do just that. One of the latest stabs at engagement is table-top tablets from Ziosk, digital devices that are part menu, part waiter, part entertainment device, and part survey platform.

Used by Chili's, Red Robin, Abuelo's and other chains and deployed at more than 1,400 locations with 77,000-plus devices, Ziosk tablets give diners the option to browse a digital menu, place orders, request another round, play games, get social, and sign up for promotions. There's also a card reader attached to the 7-inch, Android-based device so diners can swipe their credit cards and pay without having to wait for a check. For the restaurant chain, Ziosk tablets offer a way to deliver promotions, improve service, conduct customer-satisfaction surveys, and gather intelligence on the dining experience.

[ Want more on Microsoft's analytics plans? Read Microsoft Buying Revolution Analytics For Deeper Data Analysis. ]

How does Ziosk make sense of the data streaming in from 77,000-plus tablets? Part of that challenge is straightforward, as the Ziosk platform supports ordering food and paying checks, and for these functions it integrates with POS and loyalty program systems. Ziosk keeps a record of transactional information in an on-premises, Microsoft SQL Server-based data warehouse and can provide BI-style reporting at various levels, from individual stores to regions and headquarters.  

As for the rest of the data, Ziosk uses Azure HDInsight, Microsoft's cloud-based Hadoop service, to capture and aggregate anonymized transactional records along with contextual information, including click paths on each device, promotions delivered during a visit, email club enrollments, and other interactions. Thus far, Ziosk has collected several terabytes worth of data.

The Ziosk 7-inch table-top tablet lets diners browse the menu, order food and drinks, play games, call for service, sign up for promotions, and swipe credit cards to pay the check.

The Ziosk 7-inch table-top tablet lets diners browse the menu, order food and drinks, play games, call for service, sign up for promotions, and swipe credit cards to pay the check.

Ziosk chose HDInsights "because it can be difficult to do aggregations in a relational database," says Kevin Mowry, Ziosk's chief software architect. "We wanted to use a big data tool so we could look at textual information and other data types and formats that tell us what people are seeing, what they're clicking on, and how much time they're spending on the device."

Once aggregations of interest are available, Ziosk uses the Azure Machine Learning (Azure ML) service to spot patterns of behavior at different time periods within visits, whether it's arrival, ordering, dining, ordering desert, or paying the check.

"Given these buckets of time, we look at how on-screen promotions influence the guest purchase behavior," says Mowry. "We're exploring whether we can do a better job of offering the right kinds of promotions when the guest is most receptive so we can increase business."

Visualizing Azure ML results through Power BI, Microsoft's cloud-based data-visualization environment, Ziosk has learned, for example, that guests that order beverages within the first five minutes of arrival are more likely than other customers to play games. Ziosk can then alter pre-scripted triggers to deliver gaming promotions soon after beverages are ordered.

At this writing, Ziosk is still doing modeling and predictive work to learn about customer behavior patterns. The vision is to eventually run Ziosk interactions against predictive models in real-time so each diner will have a dynamic, interactive experience.

"A lot of our customers are interested in doing A-B testing, and this is one of the tools we can provide to evaluate the effectiveness of different tests that we're doing inside the restaurant," Mowry said.

Ziosk isn't the only provider of interactive, table-top devices. Applebee’s and Johnny Rockets are rolling out tablets developed by E la Carte Inc. We can't predict that every diner will like this sort of digital dining experience, but there's no doubt that we're going to see more of these devices in bars and restaurants near you.

Attend Interop Las Vegas, the leading independent technology conference and expo series designed to inspire, inform, and connect the world's IT community. In 2015, look for all new programs, networking opportunities, and classes that will help you set your organization’s IT action plan. It happens April 27 to May 1. Register with Discount Code MPOIWK for $200 off Total Access & Conference Passes.

Doug Henschen is Executive Editor of InformationWeek, where he covers the intersection of enterprise applications with information management, business intelligence, big data and analytics. He previously served as editor in chief of Intelligent Enterprise, editor in chief of ... View Full Bio

We welcome your comments on this topic on our social media channels, or [contact us directly] with questions about the site.
Comment  | 
Email This  | 
Print  | 
RSS
More Insights
Copyright © 2019 UBM Electronics, A UBM company, All rights reserved. Privacy Policy | Terms of Service