Recognizing Students At-Danger With Early Intervention Using Machine Learning Techniques

Students in online courses require attention as there is no much interaction between the teacher and student compared to traditional instructing methods. Due to the increase in advent of massive open online courses, there is a need to focus on identifying students at danger of withdrawl or failure. As the count of students enrolling in an online course is huge it's quite difficult to find out specific students who are at-danger of failure/withdrawal from the course. There is a need to alleviate this problem by identifying those students and help academic instructors offer support to them. The major contribution of this work is to analyze the risk associated with the dropout of student in order to aid instructors in delivering the intensive intervention support to student who is at verge of quitting from the course. The main objective is to track student performance and provide valuable information to the educator to subsequent the courses according to their learning achievement and also help academic advisors to detect the student having low academic achievement records and encourage the candidates. Data collected from OULAD datset is analyzed with the help at -risk prediction model is to identify whether a student is at verge of withdrawal or not.