Skip to main content

Leveraging machine learning to retain customers

Donatos Pizza had a mountain of consumer data, but they didn’t have the systems in place to capitalize on it. This disconnect from their data directly led to a drop in customer retention and declining sales in several markets.
Leveraging machine learning to retain customers


Standing out in a saturated market
National pizza brands have massive marketing budgets and immediate brand recognition. Donatos needed to stand out from those brands, but they didn’t have a data-driven strategy in place for how they could differentiate from competitors. Their message and marketing got lost in the noise of competition, often costing them returning customers.
Converting new customers to returning customers
Donatos wanted to identify customers who were at risk of leaving so they could take action to win them back. Without the ability to derive analytics from their data and gain insight into consumer behavior, strategic planning was unsuccessful.
Achieving company-wide growth
With over 160 stores, Donatos Pizza had many that were succeeding, but weak customer retention meant that many stores were struggling. The leaders needed a solution to increase sales in these stores to achieve consistent and company-wide growth.


Donatos Pizza wanted to look at data solutions that would lead to increased customer retention. Through a prior statistical analysis, company leaders knew that if customers returned within a specific time frame from their prior visit, they were likely to become long-term or loyal customers. Those who didn’t return were unlikely to return at all. They wanted to identify at-risk customers and target them with successful strategies to regain their business and loyalty.  

Fusion Alliance sat down with Donatos to discuss their goals and determine the right course of action. Because they had a vast quantity of customer data readily available, we knew machine learning would offer the best opportunity to identify patterns and predict consumer behavior. 

Fusion Alliance created a three-month pilot program to implement and apply machine learning models in specific stores. We predicted that at the end of the program, the stores using machine learning would retain 30 percent of the identified at-risk customers.   

Project goal

Identify the algorithm that would produce the most accurate predictive analysis 

The value of results is directly dependent on the value of data the platform receives. With so much data available, we needed to be very specific in what we used and which algorithms we identified as the most accurate.  

Our solution
  • Assess the quality and quantity of data 
  • Develop predictive models 
  • Clean the data to use as a training set and use it to identify the best algorithm for accurate predictive models 
Project Goal

Accelerate the process while reducing costs

Machine learning and predictive analytics are often very expensive and risky. Fusion minimizes risk and cost through a use-case-driven strategy, where we start with the use case, pull in only necessary data, and create an iterative approach to deliver a working solution that brings more value to the client on a faster timeline.   

Our solution
  • Start with the use case. Specifically, identifying at-risk customers
  • Extract, transfer, and load Donatos’ data on a cloud platform to improve efficiency 
  • Evaluate and select the data most likely to provide accurate insight including pulling in source data, aggregating it, and removing aberrations
Project Goal

Hone in on a specific question to enter into the machine learning models to identify at-risk customers. 

Machine learning offers the best outcomes when there is a specific, defined problem to solve 

Our solution
  • Formulate and test questions  
  •  Iterate over the model to achieve a desired state 
  • Run the previous day’s sales against the model to produce a list of at-risk customers 



Using machine learning, Donatos Pizza was able to put their data to work for them and maximize its value. By only focusing on a single use-case, we reduced costs while producing fast, accurate results. 

retention of at-risk customers
higher overall customer retention
stores roll out machine learning


Each day, we ran the prior day’s sales against the model to produce a list of customers whose risk of leaving was higher than a threshold percentage. By receiving a daily list of customers who they were at risk of losing, store managers could offer customers incentives to return. This proved highly effective and led to all 160+ stores adopting machine learning solutions.  


Proof of Concept


This successful proof of concept opens the door to exploring additional ways to leverage machine learning to solve Donatos’ business challenges. Machine learning for customer retention is only one use case. The same tactic can also be used to create strategies to reduce prices, maximize supply chain efficiencies, and optimize stock replenishment while reducing spending, improving customer loyalty, and increasing sales.  

Fusion harnessed Donatos’ robust data practice to turn their data into highly valuable predictive analytics that provided better results for both the stores and their customers.  

Ready to talk?

Let us know how we can help you out, and one of our experts will be in touch right away.