Predicting Indian Master's and PhD Enrollment using Data Mining & Machine Learning Approaches

Every year, after acquiring their undergraduate degrees, a large number of Indian students plan to continue their education overseas. Selecting a university to pursue further education may be a difficult undertaking for students. Students who have ordinary or lower academic credentials-that is, those with undergraduate assessments, English proficiency test results, work experience, and research experiences-find it difficult to select colleges that fit their needs. This research examines actual, distinct data from Indian students who were admitted to various universities throughout the world to pursue postgraduate education. Lastly, using RF (random forest) and DT (decision tree) methodologies, we have created prediction models that, depending on students' prior academic achievement, may identify suitable colleges for them in certain classes. This study examines two distinct models: one being Master [M S] scholars & additional being PhD (Doctoral degree) students. Eight classes for PhD candidates and nine classes for MS pupils make up the educational institutions where the students were admitted, accordance through latest Quacquarelli Symonds (Q S) World Rankings of University's. The two distinct machine learning methods have been examined regarding parameter (Accuracy, Precision, Recall, & Fl-Score). Based on numerical results, the algorithms DT & RF have a similar precision as 89% for data from PhD students and 86% for data from MS students.