Data Mining Techniques on Educational Databases: A Case Study, Iranian Administration System Dataset

Data mining techniques can be used to extract meaningful knowledge and useful information from the data; consequently assisting educational institutions in better allocating resources and staff. The main goal of this study is to use data mining techniques in analyzing the effects of different aspects of family background, and the socioeconomic status of parents on educational performance of applicants in Wide Entrance Examination (WEE): university admission system in Iran. This research deals with specific WEE data created and collected over 10 years by NOET (National Organization of Educational Testing). In order to investigate the effects of family background factors and other related variables on educational performance (entrance examination grades) we apply various statistical methods and data mining. The results of this analysis show that on one hand parental education, parental occupation and the socioeconomic status of family have a large effect on entrance examination grades and as a result on university and college acceptance. On the other hand the number of family members and age of applicants have a negative effect. Moreover, the proportion of acceptance in universities for the high social class families is more than the proportion of candidates in the other categories. In other words, applicants who come from higher social classes have a significantly better chance of getting admission at a university. We believe that this study provides a better understanding of the factors that could have significant impact on the applicant’s admission, and as a result on the higher education achievement. Such insights can assist decision makers about conditions and quotas applied for future exams.