No abstract

No abstract

No abstract

Many Bangladeshi students intend to pursue higher studies abroad after completing their undergraduate degrees every year. Choosing a university for higher education is a challenging task for students. Especially, the students with average and lower academic credentials (undergraduate grades, English proficiency test scores, job, and research experiences) can hardly choose the universities that could match their profile. In this paper, we have analyzed some real unique data of Bangladeshi students who had been accepted admissions at different universities worldwide for higher studies. Finally, we have produced prediction models based on random forest (RF) and decision tree (DT) techniques, which can predict appropriate universities of specific classes for students according to their past academic performances. Two separate models have been studied in this paper, one for Masters (MS)students and another for Doctor of Philosophy (PhD)students. According to the Quacquarelli Symonds (QS) World University Rankings, the universities where the students got admitted have been divided into 9 classes for MS students and 8 classes for PhD students. Accuracy, precision, recall and F1-Score have been studied for the two machine learning algorithms. Numerical results show that both the algorithm DT and RF have the same accuracy of 89% for PhD student data and 86% for MS student data.

No abstract