The objective of this paper is to provide a solid framework for the comparative evaluation of driving efficiency based on Data Envelopment Analysis (DEA). The analysis considers each driver as a Decision Making Unit (DMU) and aims to provide a relative efficiency measure to compare different drivers based on their driving performance. The last is defined based on a set of driving analytics (e.g. distance travelled, speed, accelerations, braking, cornering and smartphone usage) collected using an innovative data collection scheme, which is based on the continuous recording of personalized driving behavior analytics in real time, using smartphone device sensors. Efficiency is examined in terms of speed limit violation, driving distraction, aggressiveness and safety on urban, rural and highway road and in an overall model. DEA models are identifying the most efficient drivers that lie on the efficiency frontier and act as peers for the rest of the non-efficient drivers. The proposed methodological framework is tested on data from fifty-six (56) drivers during a 7-months driving experiment. Findings help distinguish the most efficient drivers from those that are less efficient. Moreover, the efficient level of inputs and outputs that should be reached by each one of the less-efficient and non-efficient drivers to switch to the efficiency frontier and become efficient is identified. Results also provide a potential for classification of the driving sample based on drivers’ comparative efficiency. The main characteristics of the most and less efficient drivers are consequently analyzed and presented herein. The impact of this methodology lies on the fact that most common inefficient driving practices are identified (aggressive, risky driving etc.) and driving behavior is comparatively evaluated and analyzed.
|Tags||big data, driver behaviour, machine learning, naturalistic driving, statistical modelling, telematics|