Capital One Auto Navigator

We’re offering festival goers a sneak view into how we’re using human-centered design, cutting-edge, immersive technology, extensive auto industry expertise, and unique partnerships to redefine the car-buying process during the 2018 SXSW Interactive Festival.

The Problem

Do you recall how much time you invested at the dealership when you purchased your most recent vehicle? Did you leave with your keys in hand and full faith in your purchase?

According to a recent survey commissioned by Capital One, 50% of individuals claim that purchasing a car and doing research on it take more time than determining where to go college or picking a child’s name. Furthermore, only 62% of car purchasers are completely certain they received a terrific deal the previous time they purchased a vehicle. In addition, 78% of Americans said that the last time they bought a car, they lost faith in their ability to find the automobile they wanted while shopping.

We questioned why something as joyful as purchasing a new car needed to be so stressful. As we learned more about the car-buying process, we came to the conclusion that some buyers become disheartened when they learn that their monthly payments will be (much) higher than they had anticipated because the overall cost of ownership will be higher than the purchase price of the vehicle. But frequently, when they first start shopping and have their eyes set on a certain car, they are unaware of this. Next, what? Has the drawing board been reopened? Do they start afresh or do they settle for something more expensive?

The Solution

These consumer pain points proved to be an issue that we wanted to address, so in 2015, Capital One unveiled the initial iteration of Auto Navigator, a cloud-based online application driven by a number of technologies, including machine learning and built on a micro services architecture.

Customers can now find, finance, and complete their next automobile purchase with ease, convenience, and confidence thanks to this advancement, which made the car purchasing experience simpler for them.

Customers could browse more than three million cars from more than 12,000 participating dealers across the nation with the second generation of our platform, which was released just a year later in 2016! We used real-time data to estimate what clients would spend for any of the cars in our database in the configurations of their choice (e.g., cash down, terms, etc.). More significantly, before visiting a dealership, customers could now pre-qualify for financing without having their credit score affected.

In order to continuously build, fail forward, and improve our user experience, we have iterated on Auto Navigator from its birth. To do this, we employ empathic listening, observation techniques, and rapid prototyping with consumers.

What’s Next in this Disruptive Journey?

For the benefit of the consumer, we are in this company to challenge the market. We’re showcasing the most recent iteration of Auto Navigator at SXSW in the form of a fresh feature:

Augmented Reality Feature: We have come to understand that even when clients are not actively trying to purchase a car, they are still conducting ongoing research on cars. Through the Capital One Mobile app, we want to provide our clients with an augmented reality experience in the upcoming months that will enable them to scan cars with their smartphones and read specific information about each car. Information like their pre-qualified finance, their anticipated monthly payment, nearby dealerships where they may purchase the car, and much more should be included in this. Imagine allowing customers to obtain this kind of personalised information right when they need it!

The Tech Behind It

When it debuts, the augmented reality feature will use proprietary models from Capital One as well as Apple’s recently unveiled augmented reality framework (ARKit) and new mobile machine learning framework (CoreML). Using ARCore and Tensorflow mobile, the capability is also compatible with Android devices.

While CoreML enables us to take images from the video stream and feed them through our Convolutional Neural Network to generate predictions about the car, ARKit enables us to detect surfaces and planes and create a 3D scene that we can then use to place our AR items. Customers may scan several automobiles in one session thanks to our experience optimization, and they can also access more information about a car they’ve already scanned (even after scanning several). The offer is then tailored using Capital One’s in-house models so the customer can view their projected monthly payment.

At the core of what we do is giving people the tools they need to feel secure in their relationship with money, and with Auto Navigator, we’ve discovered a way to do this while offering a top-notch digital experience that more seamlessly integrates into people’s lives.

These opinions are those of the author. Unless noted otherwise in this post, Capital One is not affiliated with, nor is it endorsed by, any of the companies mentioned. All trademarks and other intellectual property used or displayed are the ownership of their respective owners. This article is © 2018 Capital One.

Leave a Comment