Predicting Students Academic Performance Using Support Vector Machine

Education, more often known as learning, is a way of exchanging knowledge with the perspective of betterment of individuals and progress of the nation as well. The objective of this paper is to help students to improve their performance with the use of applications of data mining. It makes use of psychological features of students. The paper uses multi classifier Support Vector Machine (SVM) to classify the learners in the category of high, average and low according to their academic scores. It is carried out using linear kernel and radial basis kernel. It is noted that RBF produces better results as compared to the linear kernel. Predicting the performance of students in advance can advantage both the institution and learner to take measurable steps in order to enhance the learning process.