Domino’s Pizza Enterprises Delivers in Record Time Using AWS for Predictive Ordering

Domino’s turned to Amazon Web Services (AWS) and Max Kelsen, an Advanced Consulting Partner in the AWS Partner Network (APN), to help create a predictive ordering solution. “We knew we needed a smart, accurate system, and we liked what we saw in AWS machine learning technologies,” says Gillespie. “We knew that by using AWS services we could develop a solution that would give our stores a glimpse into the future by predicting what pizzas would be ordered next.”

The company created a data lake consisting of key order information by taking advantage of Amazon Simple Storage Service (Amazon S3) for data storage and AWS Glue for data querying. It also uses Amazon SageMaker to build and train machine learning models to predict the likelihood that an order will be placed, so a store can begin making that order right before it is placed.

As a trial, Domino’s initially deployed its predictive ordering solution in some of its stores in Australia. Store employees could view an ordering screen displaying specific pizzas with various color indicators corresponding to the likelihood of those pizzas being ordered. “This isn’t making pizzas and leaving them in a hot box for half an hour—this is getting the pizzas lined up, coming out of the oven, and ready to go as an order is placed,” Gillespie says.

The company enhanced the solution during the trial so it would be ready for a wider rollout. Domino’s then began deploying the solution to stores in New Zealand, France, the Netherlands, Japan, and Germany.

Using the AWS-based solution, Domino’s has given its stores a tool to help drive down pickup and delivery times for customers. For example, in 2019, a Domino’s store in Australia averaged delivery times of under 5 minutes, from order to doorstep, across an entire week. “It’s exciting that nothing changes from the customer’s perspective, except that the post-order experience can be much quicker,” says Gillespie. “Customers are getting their pizza faster, hotter, and fresher because of the improvements we’ve put into place with Project 3TEN. The predictive ordering solution we developed by using AWS is a big part of that.”

Domino’s is gaining a competitive advantage in the marketplace. “When our customers are hungry, they’re hungry now, and we want to deliver their meal as quickly and safely as possible,” says Allan Collins, chief marketing officer for Australia and New Zealand at Domino’s. “That’s our market differentiator. Some of our competitors still take 45 minutes to an hour to deliver a meal, when we can have a pizza delivered in 10 minutes or less following an order. That really impresses our customers.”