In this paper, the relation among factors in the road transportation sector from March, 2005 to March, 2011 is analyzed. Most of the previous studies have economical point of view on gasoline consumption. Here, a new approach is proposed in which different data mining techniques are used to extract meaningful relations between the aforementioned factors. The main and dependent factor is gasoline consumption. First, the data gathered from different organizations is analyzed by feature selection algorithm to investigate how many of these independent factors have influential effect on the dependent factor. A few of these factors were determined as unimportant and were deleted from the analysis. Two association rule mining algorithms, Apriori and Carma are used to analyze these data. These data which are continuous cannot be handled by these two algorithms. Therefore, the two-step clustering algorithm is used to discretize the data. Association rule mining analysis shows that fewer vehicles, gasoline rationing, and high taxi trips are the main factors that caused low gasoline consumption. Carma results show that the number of taxi trips increase after gasoline rationing. Results also showed that Carma can reach all rules that are achieved by Apriori algorithm. Finaly it showed that association rule mining algorithm results are more informative than statistical correlation analysis.