Prediction model for classifying students based on performance using machine learning techniques

Abstract

In today’s competitive world of educational organizations, the universities and colleges are using various data mining tools and techniques to improve the students’ performance. Now a days, when the number of drop out students is increasing every year, if we get to know the probability of a student whether he/she will be able to cope up easily with the course, it is possible to take some preventive actions beforehand. In other words, if we get to know that a student will clear his papers in the course or he will have reappear in papers, a teacher/parent can focus more on such students. The data set of students has been taken from the UCI Machine Learning repository where a sample of 131 students have been provided with twenty-two attributes. The results of six classification algorithms have been compared in order to predict the most appropriate model for classifying whether a student will have a reappear in a course or not.