Guest Post: How Connected Car Platforms Based on Artificial Intelligence Can Empower Your Business Today

Sign in to queue


The following is a guest blog post by Alex Dimchenko, CSO, Bright Box.

Most car manufacturers are either in the process of launching or already have launched their own connected vehicle platform. A consequence of this process is the accumulation of a massive quantity of data from connected vehicles and connected drivers.

Experts predict that by 2020 there will be roughly 152 million connected cars on the road, with each generating up to 30 terabytes of data daily. What should we do with the data that has already been accumulated, and how can we put it to work for our business? How can we use this information properly to achieve the most success possible?

In our opinion, a key factor in formulating the task of working with data is the use of predictive analytics and AI-based solutions.

All the information collected from every vehicle -- trips, telemetry, engine RPMs, speeding up and slowing down, incidents, etc. -- needs to be used to make people's lives easier, both for users and for business. From the perspective of ecosystem players, AI data processing will help to attract insurance companies and parking and car-sharing services to the ecosystem -- companies that know how to monetize data.

On the other hand, by using AI we can analyze and predict drivers' consumer behavior -- what they like to do, how they like to use their cars -- and, most importantly, understand their future needs and what kind of car or accessory they're going to need tomorrow if their lifestyle changes. For example, if a driver has a baby, by using AI  we can offer them a somewhat larger car or a child seat; if they travel frequently, we can give them the opportunity to replace their tires in a timely way.

Generic Image

This year our company implements an Artificial Intelligence service based on Connected Car Platform data. This AI can evaluate the customer's lifestyle and recommend accessories, and can sell cars based on driving style and the individual's lifestyle.

Not only that, it is able to predict when the user needs to go in for a service from the data generated from the telematic control unit or OBD dongle. The new system is based on work that Bright Box has done with the processing of 1.5 terabytes of data from connected car users from various countries.

We have created a Microsoft Azure Data Lake, where the terabytes of data gathered from cars are stored in a structured fashion. Upsell forecasts are based on the data from Telematics (mileage, GPS, speed, RPM), as well as from CRM, DMS or ERP systems (customer ID, date of the transaction, breakdowns by work/materials).

It can bring insights to light based on this data. For example, we can calculate 160 insights that we consider important: the portion of driving time spent at speeds of over 80 mph, how frequently the driver steps on the gas, where they go most frequently in an urban setting or in the country, passenger doors opening, high RPM etc.

Data is constantly being accumulated and analyzed from all available sources. For every user, we have a certain number of indicators that characterize only that user. These data sets enrich and complement each other, allowing you to find a lot more insights and draw more valuable conclusions about the drivers' behavior.

We can determine the likelihood of a response to an offer from a dealer based on every driver's indicators. If this probability reaches a certain value required to trigger a marketing or service campaign, a push notification is sent to the user's email or phone. The car owner receives a minimally interactive message. If the customer is interested, Remoto AI offers to send them an application, open a chat window, or schedule a return call from a dealer for further communication. The customer's reaction affects the evaluation of the probability of their responding to similar offers in the future.

The AI learns from all the data that has been collected. It works based on the driver's behavior, on the "look-alike" principle with very high probability. Using AI we created associative rules, which is one of the most common approaches. Let's assume that a car owner often purchases new tires when visiting a dealership for planned service. This helps us create a rule that IF the driver comes for service, he or she will buy new tires as well.

AI can be used to replace service consultants -- from a hosting perspective, it would be impossible to provide every car owner with a consultant. Therefore, a typical consultant at a dealership works with an average of 100 customers. Bright Box enables dealerships to provide a personal consultant to every customer in the form of an intelligent application. This way, a dealership can increase sales and service quality by 100 times or more! Dealers can use this system to automatically improve their level of service and customer interaction. The potential gain in effectiveness, cost-efficiency, and customer satisfaction is truly great.

If you would like to learn how to power up your car business with AI today, contact me. If you fill out the form on our website, we will also send you a presentation and respond to any questions you might have. Also visit our site to download a free sample of the white paper, "How Connected Car Platform based on AI empower your business."

The Discussion

Add Your 2 Cents