A Capital One
success story

Capital One scales real-time auto loan decisioning with Akka

The need

According to a recent survey commissioned by Capital One, 50% of people report researching and buying a car is more time-consuming than deciding where to go to college. In addition, 62% of car buyers are not fully confident they got a great deal the last time they bought a car, and 78% admit they lost confidence that they would get the car they wanted during the shopping process.

Fred Crable, Senior Director of Data Engineering and Augmented Intelligence at Capital One, asked his team to find out why buying a new car was fraught with so much anxiety. As the team dug deeper, they found that buyers would often set their hearts on a particular car, only to find out at the end of the process that the total payments were higher than they expected, putting the car out of their price range. This was a discouraging experience, which often left buyers feeling that they had been forced to settle for less.

The challenge

Capital One believed there had to be a better way for car buyers, dealers, and banks, and decided to re-imagine the car-shopping experience by building a new, high-performance platform for real-time auto financing.

“This was open heart surgery for the business,” Crable said. “Trying to optimize the best loans for the customer. No one likes waiting, especially for loan approvals. So, when my team needed to upgrade our auto financing loan origination systems for real-time decision-making at high scale, we brought in Akka with Spark and Cassandra to create a brand-new customer experience.”

The solution

In 2015, Capital One introduced the first version of Auto Navigator, a cloud-based web application built on a micro-services architecture and powered by a suite of technologies, including machine learning.

Building this new application using Akka delivered blazing-fast results for Capital One. Driving the application was an architecture based on Akka and its actor model at the core, with Apache Kafka for the messaging queue.

Crable comments: “We used the full spectrum of reactive tools and launched Auto Navigator in the cloud on Amazon Web Services with all the real-time tracking, escalation paths, monitoring and auditing you need for our industry.”

The results

According to Cradle, when testing Auto Navigator on a simple laptop, the new solution was able to support 486 loan applications per minute. By contrast, the old platform could only process 100 applications per minute, even though it was running on a cluster of servers.

Moreover, while the old architecture could take more than two days to process the data required by Auto Navigator, the new architecture built on Akka was able to support up to 16 simultaneous users with 180 to 200 millisecond response times.

In a second iteration of the application, Crable and his team leveraged real-time data, which allowed them to determine how much customers would pay for any of the cars in their database for any of the financing options they choose—and get the results in around one second. More importantly, customers could now pre-qualify for financing with no impact to their credit score before ever stepping into a dealership.

By building the new architecture for Auto Navigator using Akka, Capital One has been able to simplify the car shopping process for customers—allowing them to browse nearly four million cars from over 12,000 participating dealers across the country, and find, finance, and fulfill their next car purchase with ease, convenience, and confidence.

MORE SUCCESS STORIES

Stay Responsive
to Change.

GET STARTED
CONTACT US