Evaluation of Student Performance with Predicted Learning Curve Based on Grey Models for Personalized Tutoring

Abstract

Learning time of student is precious, over-practice of target knowledge component wastes student’s time, however, under-practice may mean the student may not grasp target knowledge component properly. To any student, it is helpful if intelligent tutoring system can determine how many practice opportunities needed for mastery of knowledge component. In this paper, to improve student’s learning efficiency, a method of predicted learning curve based on grey models is proposed to determine the counts of practice op-portunity for mastery of knowledge component. The experimental results show that the predicted value on error rate of practice opportunity over knowledge component with the proposed method is much closer to the value of real learning curve than the predicted learning curve produced by learning factors analysis. It implies the proposed prediction method is potential to present reasonable practices for personalized tutoring.