Applying fuzzy clustering to assess and anticipate students' educational progress in learning environments

The purpose of this paper is to propose a method to anticipate students' proceed and to enhance their learning efficiency and success in a learning environment, using data mining. Based on library and survey searching methods, as well as consulting with experts, some effective features in students' learning are identified and then using feature selection method, the most efficient ones are chosen. To clarify the relation between selected features, fuzzy clustering is applied to them. In the second phase of the research, scores of the students of Educational environment study, are predicted, using data mining. Variables taken are midterm and final scores and the average score of selected units in one semester by students studying there between 2006 (1385) and 2012 (1391). According to the achieved methods we can guide each student from the beginning of the semester in line with their effective features, and based on scores gained during the semester we can inform the student about his range of final score to receive an educational plan based on his/her abilities. These methods can be effective in streamlining learning procedure in a system. Test results show the desired accuracy (0.939) of the proposed method than previous methods (discovery of association rules, classification, and identifying the inconsistencies).