Auto Navigator: Disruption of the car purchase in the interest of the customer
Sanjiv Yajnik, President of Financial Services, Capital One
 |
| Image Source - Google | Image by - makkitv2 |
At the interactive SXSW 2018 festival, we're giving festival-goers a glimpse of how we're using human-centered design, forward-leaning, immersive technology, deep automotive industry expertise, and innovative partnerships to reinvent the car buying process.
Problem
Do you remember how much time you spent at the dealership when you bought your last car? Did you walk away with the keys in hand and feel confident about your purchase?
When it comes to big life decisions, 50% of people say researching and buying a car is more time-consuming than deciding where to go to college and choosing a name for a child, according to a recent survey commissioned by Capital One. Additionally, 62% of car buyers aren't quite sure they got a great deal on their last car purchase. Additionally, 78% of Americans admit that the last time they bought a car, they lost confidence that they would get the car they wanted during the buying process.
We asked ourselves why something as exciting as buying a new car had to be fraught with so much anxiety. What we've realized as we delve deeper into the car buying process is that some people are disgusted when they realize that the payments are (much) higher than they expected because the total cost of ownership is higher than the price of the car. But they often don't know this at the beginning of the buying process when they set their sights on a particular car. And then what? Is it back to the drawing board? Will they start over or settle for something outside their budget?
Solution
These customer pain points emerged as a problem we wanted to solve, so in 2015 Capital One introduced the first version of Auto Navigator, a cloud-based web application built on a microservices architecture and powered by a set of technologies. , including machine learning.
These developments have simplified the car buying process for customers – enabling them to find, finance and complete their next car purchase with ease, convenience and confidence.
With our second iteration, introduced just one year later in 2016, customers were able to view over three million cars from over 12,000 participating dealers nationwide! We used real-time data, which allowed us to determine how much customers would pay for any of the cars in our database for any combination they choose (eg cash, terms, etc.). More importantly, customers could now pre-qualify for financing without impacting their credit scores before even entering the dealership.
We've used Auto Navigator since the beginning, implementing human-centered design where we use empathic listening, observational techniques, and rapid prototyping with customers to constantly build, fail, and rapidly improve our customer experience.
What's next in this disruptive journey?
We are in this business to challenge the market for the benefit of the customer. At SXSW, we're introducing the latest evolution of Auto Navigator in the form of a new feature:
Augmented Reality Features: We've realized that car research is an ongoing process that customers engage in even when they're not actively considering buying a car. In the coming months, we plan to offer our customers an augmented reality experience through the Capital One Mobile app, which will allow them to scan cars through their mobile phones and view individual information about each car. This could include information such as their pre-qualified financing, their estimated monthly payment, the nearest dealership where they could purchase the car, and much more. Imagine customers being able to access this type of personalized information at the point of need and in real time!
The technique behind it
At launch, the Augmented Reality feature will use Apple's recently announced Augmented Reality Framework (ARKit) and their new Mobile Machine Learning Framework (CoreML), as well as Capital One's proprietary models to identify and price cars. This feature is also compatible with Android using ARCore and Tensorflow mobile.
ARKit allows us to detect surfaces and planes and create a 3D scene that we can then use to position our AR assets, while CoreML allows us to take images from a video stream and feed them to our convolutional neural network to make predictions about the vehicle. We have optimized the experience so that customers can scan multiple cars in one session and get more information about the car they have already scanned (even after scanning several). We then use Capital One's proprietary models to tailor the quote so they see their estimated monthly payment.
Empowering people to be confident about their relationship with their money is at the core of what we do, and with Auto Navigator we've found a way to achieve that while providing a seamless digital experience that fits more naturally into people's lives.
These opinions are those of the author. Unless otherwise stated in this post, Capital One is not affiliated with or endorsed by any of the companies mentioned. All trademarks and other intellectual property used or displayed are the property of their respective owners. This article is © 2018 Capital One.