How data changes workshops’ customer service from being reactive to proactive
With the utilisation of car data, the automotive industry is going through a revolution. Data can now show us a vast amount of rich information about a car, from its technical conditions to handling or usage; and with this, workshop’s approach to customer service can be changed drastically too. In this article, we would like to present the new perspective data can give workshops in their customer service.
Data-driven maintenance approach — from reactive to proactive
If you experience a severe problem with your non-connected car (for e.g your battery is draining and you cannot start your car in the morning) your workshop will only know and be able to react to this after this has happened and you have called them. However, if your car is connected to your workshop, the real-time data about the status of your car is not only able to help your service advisor to understand the problem when it happens, but also alerts you while it is happening, perhaps before you notice yourself. In a connected car — among many things — the battery health is collected every couple of hours and if we detect a draining battery or a battery with a consistently low voltage the service advisor is able to proactively contact you and help you get the problem solved. This way the workshop can transform their service from reactive to proactive.
Data-driven and predictive maintenance are able to identify possible maintenance issues before they even happen with the help of advanced data analytics. These methods learn from the patterns in the sensor data from the individual car as well as the collected knowledge from the population of the cars.
With this data-driven approach, the workshops are able to significantly reduce car downtime and address problems early on before they become more costly. Additionally, this approach can reduce costs for the driver, workshops can prepare ahead and provide a seamless customer experience. From our Workshop tool service advisors can easily send chat messages, book a time and even send quotes after the service making the experience smooth and effortless than ever before.
Real-life examples of data-driven maintenance
Every day we receive around 15 million data points related to service and oil changes alone. For some cars predicting the next scheduled service or oil change is as easy as mirroring the data in the car. For other cars with less advanced data possibility individually tailored predictions are generated based on how the car is driven. In both cases, the workshop can list the predicted dates of the service visits and not only notify the customers through the chat and notification system but is also able to plan work in advance and proactively suggest suitable time slots.
Another example is the aforementioned detection of battery problems. If a battery problem is detected the service advisor is allowed to see the battery voltage graph from the last 7 days. Normally a healthy battery has a voltage around 12.6V when the car is not in use. If the battery is draining or is not able to recharge to 12.6 after trips it indicates a problem that can cover anything from attached extra equipment draining the battery to defective generator or battery in bad health. Below are examples of voltages graphs of batteries in good and bad shape. In the latter, the battery is not able to recharge to the normal voltage even after it has been driven and if this problem is not addressed, will cause the car to be unable to start after a certain time or when the weather gets cold.
Monitoring the battery health of thousands of cars connected to a single workshop one by one would be a daunting task for a service advisor, so all connected cars are monitored 24/7 through algorithms and alerts. Notifications are generated if problems are observed to the workshop and customer. With these insights, the service advisor can be proactive and book the driver ahead of time. This changes customer service from being reactive to proactive.
The future of maintenance is predictive
Predictive maintenance in general is the ability to foresee problems before they happen. This requires a huge amount of both historical and current data to make it possible to help drivers before the problems happen. Predicting failing spare parts is, in particular, a very promising and interesting topic which is already in active development at Connected Cars. Together with the already existing data-driven and predictive models such as the mentioned battery and service/oil change elements of the workshop tool we are very excited to be on this journey towards helping customers and workshops getting connected.
