This paper is aimed to investigate application potential of data mining in automotive industry. Most important usage and driving parameters, which effects fuel consumption and emission level of passenger cars identified and classified by using data mining methods. A dataset created by combining Euro 6 data of passenger cars has been analyzed using different tools of SPSS, such as; descriptive statistics, correlations, regression and etc. Results have been compared and effecting parameters have been derived by segmentation algorithms aiming better results by categorizing variables for upcoming analysis. The importance of each parameter has been evaluated to predict its contribution on fuel consumption by data mining technics. Therefore, it will be possible to build optimal control strategies for fuel efficiency for future cars, such as; electric, connected and automated vehicles. Adopted data mining technics in this study are classification algorithms, such as; neural networks, Bayesian networks and C5.0 algorithm as well as segmentation algorithms (e.g. K-means and Two-step) targeting foreseeability and simplicity. Application of those technics by Clementine 12.0 has shown that weight and engine capacity of passenger cars were the most important parameters in fuel consumption, respectively. Depending on the evaluation of the performance of those methods by Evaluation Node of Clementine, it has been found that C5.0 was the most efficient method in prediction of fuel consumption among others. However, the evaluation charts (Gain, Profit, ROI, etc.) have shown that neural network could have better results in prediction in some conditions.