Telematics is the technology of sending, receiving and storing information via telecommunication devices with the ultimate objective of controlling the remote objects in which these sensors are embedded. Automotive industry has been doing this for at least a couple of decades, but with big data becoming more accessible, this puts a new spin on a well-known technology.
The average car on the road today generates a mind-boggling amount of data. With sensors monitoring everything from tire pressure to engine RPM to oil temperature and speed, cars can quickly generate terabytes of data every hour. The vast majority of this data is used in real time to control or report on the functions of the vehicle and has not been leveraged for its long-term value. At first sight, collecting such data for long term analytics may seem redundant. For example, receiving a thousand “Tire Pressure Normal” messages from a sensor does not immediately seem to carry a lot of value, so automakers typically did not bother to store that data in the car or on the cloud. However that mind set is now changing.
Data from a large and growing number of embedded sensors can be used in a variety of ways: at the driver level to select a more personalized, convenient and efficient mode of driving, at a macroscopic (e.g. traffic) level, information collected in this way then can be consolidated to find solutions to problems like traffic jams, helping to improve the flow of traffic should city officials want to leverage this data as well. From a manufacturing perspective, close attention to fine grain data can significantly improve vehicle quality, by potentially reducing warranty and recall issues. Finally, the data collected becomes valuable for several related areas as well.
With the help of telematics it is possible to track and collect relevant car usage data. Automotive original equipment manufacturers (OEMs) can start to share this data with outside organizations to generate new revenue streams. The most obvious example here is partnerships with insurers who would like to collect a specific subset of data from cars – such as speed, time of driving, harshness of braking and cornering – to determine how drivers actually drive, rather than to base their risk calculation on far less reliable sources, like their age or past credit status.OEMs could provide this information directly to insurers, creating an appealing service for their customers as well as a revenue-sharing opportunity.
Conventional insurance rating systems are primarily based on past realized losses and the past record of other drivers with similar characteristics. More recently, electronic systems have been introduced whereby the actual driving performance of a given driver is monitored and communicated directly to the insurance company. The insurance company then assigns the driver to a risk class based on the monitored driving behavior. An individual, therefore, can be put into different risk classes on a month to month basis depending upon how they drive. For example, a driver who drives long distance at high speed in one month might be placed into a high risk class for that month and pay a large premium. If the same driver drives for short distances at low speed the next month, however, then he or she might be placed into a lower risk class and charged a lower premium. As discussed elsewhere on this blog, techniques such as decision tree algorithms can be used for credit scoring of these drivers.
Even if only some of the on-board diagnostics and telematics data is valuable, if you multiply that fraction by a billion cars that are on the road today, it is easy to understand why Big Data is attracting so much attention in the automotive space.
For more predictive analytics and big data in manufacturing, join us in Chicago during June 2014 for the launch of the Predictive Analytics World - Manufacturing conference. Do you have a manufacturing big data story to tell? Sign up to become a presenter.