Auto Navigator: Disrupting Car Buying for the Sake of the Customer
At the 2018 SXSW Interactive Festival, we’re giving festival-goers a sneak peek into how we are applying human-centred design, forward-leaning, immersive technology, deep auto industry expertise, and innovative partnerships to reimagine the car-shopping process.
Do you remember how much time you spent in the dealership when you bought your last car? Did you walk out, keys in hand, feeling fully confident in your purchase?
When it comes to big life decisions, 50% of people report researching and buying a car is more time consuming than deciding where to go to college and choosing a baby name, according to a recent survey commissioned by Capital One. In addition, 62% of car buyers are not fully confident they got a great deal the last time they bought a car. To add to that, 78% of Americans admit the last time they bought a car, they lost confidence that they would get the car they wanted during the shopping process.
We asked ourselves why something as exciting as buying a new car needs to be fraught with this much anxiety. What we realized as we dug deeper into the car-shopping process, is that some people are left discouraged, realizing the payments are (much) more than they expected because the total cost of ownership is larger than the price of the car. But oftentimes they don’t know this at the beginning of the shopping process, when they set their hearts on a particular car. Then what? Is it back to the drawing board? Do they start over, or settle for something outside of their budget?
These customer pain points proved to be a problem that we wanted to solve for, so, 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.
This development simplified the car shopping process for customers — allowing them to find, finance and fulfill their next car purchase with ease, convenience and confidence.
With our second iteration, introduced just a year later in 2016, customers could browse more than three million cars from over 12,000 participating dealers across the country! We leveraged real-time data, which allowed us to determine how much customers would pay for any of the cars in our database for any of the combinations they choose (e.g., cash down, terms, etc.). More importantly, customers could now pre-qualify for financing with no impact to their credit score before ever stepping into a dealership.
Since inception, we have iterated on Auto Navigator, implementing human-centered design where we use empathy listening, observation techniques and rapid prototyping with customers in order to continuously build, fail forward and fast and improve our customer experience.
What’s Next in this Disruptive Journey?
We are in this business to challenge the market for the sake of the customer. At SXSW, we’re previewing the latest evolution of Auto Navigator in the form of a new functionality:
- Augmented Reality Feature: We have realized that car research is a constant process that customers are engaged in, even when they are not actively looking to buy a car. In the coming months, we plan to offer an augmented reality experience to our customers through the Capital One Mobile app, allowing them to scan cars via their mobile phones to view individualized information related to each car. This could include information such as their pre-qualified financing, their estimated monthly payment, nearby dealerships where they could buy the car, and much more. Imagine customers being able to get access to this type of individualized information at the point of need, real-time!
The Tech Behind It
Upon launch, the Augmented Reality feature will leverage Apple’s recently-announced augmented reality framework (ARKit) and their new mobile machine learning framework (CoreML) as well as Capital One proprietary models to identify and price cars. The feature is also compatible with Android, using ARCore and Tensorflow mobile.
ARKit enables us to detect surfaces and planes and create a 3D scene that we can then use to place our AR assets, while CoreML allows us to take images from the video stream and pass them through our Convolutional Neural Network to get predictions about the vehicle. We’ve optimized the experience so customers can scan multiple cars in a session, and get more information about a car they’ve already scanned (even after scanning several). We then utilize Capital One’s proprietary models to customize the offer so they can see their estimated monthly payment.
Empowering people to feel confident about their relationship with their money is at the heart of what we’re doing, and with Auto Navigator, we’ve found a way to do this while providing an ultimate digital experience that fits more naturally into people’s lives.