The way a person drives is a relevant source of information to make decisions about that person, in some contexts. For instance, insurance companies set vehicle insurance fees as functions of static variables, such as the age of the driver, the number of years one holds a driving license, and the driving history. These variables may not reflect the everyday behavior of the driver on the road, thus ending up by penalizing good drivers that are young. Another example is the fleet management task, in which it is relevant to know who the best drivers are, to make the best trip planning decisions. In this paper, we follow a pay-as-you-drive approach, to devise a driver style identification approach, based on driver behavior data. Using anonymous data records with the trips from different drivers, we build a dataset and we apply unsupervised dimensionality reduction and clustering techniques. The experimental results show clusters with distinct trip styles. Many drivers show a non-aggressive driving style, some have an aggressive style and a few have a risky style.