Think Google knows too much about your daily life? Better brace for Microsoft’s Big Brother act–Predestination is MS’s experimental program that collects driving data (urban driving data, traffic patterns, your own driving patterns, etc.) to create an in-car recommendation engine that gives dynamic advice on how to efficiently get to where the system thinks you’re going.
Predestination has been under development for quite some time, as evidenced by this 2006 conference paper on the subject. The paper’s summary explains that Microsoft created its recommendation algorithm by tracking GPS data on 169
different subjects who drove 7,335 different trips. Microsoft’s algorithm takes into account different types of destinations,
driving efficiency, trip times, and “an open-world modeling methodology
that considers the likelihood of users visiting previously unobserved locations
based on trends in the data and on the background properties of locations.” That means the algorithm can predict where you’re going before you even decide to go there.
The applications for this type of machine learning go far beyond just driving, according to Greentech Media. Microsoft is using the same technology to improve data center efficiency and building management systems (i.e. lights that switch off behind you when algorithms predict that no one will reenter the room). Check out Rick Rashid, the senior vice president of Microsoft Research, explaining Predestination in the video below.