A Comparison of Machine Learning Techniques for the Prediction of the Student’s Academic Performance

Abstract

The aim of this paper to predict a student performance using traditional and machine learning techniques: Bayes algorithm, linear regression, logistic Regression, k-nn algorithm, decision tree. Naive based algorithm is the emerging field which compose the procedure of verified students details like semester marks, assignment, attendance, lab work which are used to improve students’ performance. This paper shows a model of students data prediction based on Bayes algorithm, linear regression, logistic Regression, k-nearest neighbor, decision tree and suggest the best algorithm among these algorithms based on performance details. Classification is an important area to predict and application in a variety of fields. In the view of full knowledge of the algorithm underlying probabilities, Bayes decision theory shows the optimal error rate. Decision tree algorithm is been used successfully in expert systems in capturing prediction. Mainly the decision tree classifiers are used to design and classify the student’s data with Boolean class labels. Linear regression is a linear approach to modeling the relationship between the details of students in scalar response.