Improved Decision Tree Method in E-Learning System for Predictive Student Performance System During COVID 19

E-Learning courses are top-rated in recent years. While COVID 19 primarily affects public health, spillover effects can already be observed in education, stemming mainly from extended educational institution closures. This is undoubtedly the critical time for the education sector because, during this period, many universities’ admission exams and competitive examinations are conducted. For them, we should forget about tests, admissions, etc. The need to study student success and forecast their success, along with that is increasing. With the increasing number of it was tested for instructional technology’s popularity, various data mining algorithms perfect for predicting student performance. The right algorithm depends on the algorithm’s nature. A guess has to be made by the faculty. If the number of students, the need to correct data complexity raises data relationship and their processing is an issue for the student to be found at the expense of failure. The decision tree approach to the statistical analysis of academic findings in this paper concerns and the big data implication.