Abstract—Universities are reputable institutions for higher education and therefore it is crucial that the students have satisfactory grades. Quite often it is seen that during the first few semesters many students dropout from the universities or have to struggle in order to complete the courses. One way to address the issue is early grade prediction using Machine Learning techniques, for the courses taken by the students so that the students in need can be provided special assistance by the instructors. Machine Learning Algorithms such as Linear Regression, Decision Tree Regression, Gaussian Naïve Bayes, Decision Tree Classifier have been applied on the data set to predict students’ results and to compare their accuracy. The evaluated profile data have been collected from the students of 10th semester or above of the Computer Science department, BRAC University, Dhaka, Bangladesh. The Decision Tree Classifier technique has been found to perform the best in predicting the grade, closely followed by Decision Tree Regression and Linear Regression has performed the worst.
Index Terms—Machine learning algorithms, linear regression, decision tree regression, Gaussian Naïve Bayes, Decision tree classifier, feature importance, Chi-Square.
The authors were with the Department of Computer Science and Engineering, BRAC University, 66 Mohakhali, Dhaka, Bangladesh (e- mail: sumaiyaiqbal1998@gmail.com, mahjabinmuntaha96@gmail.com, zerin.ishrat444@gmail.com, dewansakib@gmail.com).
Cite: Sumaiya Iqbal, Mahjabin Muntaha, Jerin Ishrat Natasha, and Dewan Sakib, "Early Grade Prediction Using Profile Data," International Journal of Machine Learning and Computing vol. 12, no. 5, pp. 193-201, 2022.
Copyright © 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).