Intelligent Preference Selection for Evaluating Students´ Learning Achievement

The task of evaluation for students´ learning achievement needs to consider several aspects about students´ learning performance such as practices, examinations, and observations. Traditionally, such evaluation usually calculates a final score by means of weighted average method after awards numerical scores, and then determines a grade according to a set of crisp established criteria. However, this approach lacks for reflecting the characteristics of a class against others. Several researches using fuzzy techniques to provide practical methods for evaluating students´ learning achievements for the sake of expression of linguistic terms that usually used by teaches in assessing students´ learning achievement. However, these approaches are largely based on expert opinions and have to endure complicated compute process. In this paper, we present a new method for dealing with students´ learning achievement valuation using adaptive ordered weighted averaging operator and K-nearest neighborhood classification method. The proposed method simulates the evaluation behavior of teachers to perform the student achievement evaluation based on norm-referenced evaluation by intelligent situation selection and it provides a useful way to award a reasonable grade for student.