Applying Machine Learning on automotive customer quality data to improve user experience and increase industry competitiveness 2022-36-0070

The automotive industry is going through one of its greatest restructuring, the migration from internal combustion engines to electric powered / internet connected vehicles. Adapting to a new consumer who is increasingly demanding and selective may be one of the greatest challenges of this generation, Original Equipment Manufacturers (OEM) have been struggling to keep offering a diversified variety of features to their customers while also maintaining its quality standards.

The vehicles leave the factory with an embedded SIM Card and a telematics module, which is an electronic unit to enable communication between the car, data center. Connected vehicles generate tens of gigabytes of data per hour that have the potential to be transformed into valuable information for companies, especially regarding the behavior and desires of drivers.

One of the techniques used to gather quality feedback from the customers is the NPS it consists of open questions focused on top-of-mind feedback.

Here is where AI and ML comes into play, using NLP and several other computational techniques to download, extract, structure, read, process, understand and categorize all this data into specific predetermined categories, allowing engineers to accelerate fixing quality issues and improving user experience. The ML model developed in this article identify costumer complains in an enormous data lake and groups them into categories. After a significative amount of data is collected and grouped into it enables the algorithm to predict future trends and together with real time connected vehicle data the model can alert the responsible engineers to develop an action to solve the problem without more customers even actually experience the failure.

The ML algorithm is still on its development phase, but the initial results are promising, we have successfully processed more them 6 millioncustomers feedback finding problems with precision and accuracy close to 90%.