Automotive safety is an important criterion for consumers, manufacturers and government regulators when considering vehicle design and driver operation. The availability of a driver classification system, based on in-vehicle operating data, offers a useful tool to create a safer transportation environment. In this paper, several mathematical strategies will be presented to analyse collected vehicle data for driver classification. A group of test subjects were supplied in-vehicle data acquisition devices and requested to drive their normal schedules. The collected data was analysed off-line and a driver classification system was proposed. Representative results will be presented and discussed to demonstrate the concept.