A Study On Application Of Data Mining Technology To Student Score Analysis

Data Mining can extract valid, implicit, and potential useful knowledge from large amounts of data. It has been successfully applied to many fields, but relatively seldom to the educational field. According to the regulations of teaching management system, the student score plays an important role in the evaluation of teaching quality in college. In this thesis, one technology of data mining, i.e. decision tree, is introduced into the analysis of student score to find some previously unknown factors which may influence the student score. Furthermore, these factors can be used to purposely improve the teaching quality in college.The main contents of the thesis are summarized as follows. First, the basic theory of data mining, and its application status in the educational field are introduced. Second, a database of college students' English score is created. Moreover, the C4.5 algorithm, which is a popular decision tree induction method, is adopted to infer a decision tree from the database. The learned tree is converted into an equivalent set of classification rules. Third, some primary factors influencing CET-4 score are obtained by analyzing the learned decision tree and classification rules. For example, the college English 1 influences CET-4 the most, and the passing result of CET-4 can be predicted according to scores of the college English 1 and 2. These obtained factors would be helpful to improve the college English teaching.