Comparison study of Regression Models for the prediction of post-Graduation admissions using Machine Learning Techniques

In today's technological world, a student's graduate performance plays a vital role in building either a net worthy career or opting different university for master's studies. One simple wrong decision made while Shortlisting University without the knowledge of university ranking by a student can ruin an entire year of hard work and success. A poor university choice may conflict with the student's inner gift and talent, wasting invested time and can cause confusion in choosing the right path and directions. Especially the student who is opting for a master's degree based on their GRE/TOFEL score face real difficulty in choosing different research-based universities that need a high score in these exams. This study can help the student to take a measurable step towards selecting. Our study focuses on using analytics to propose a model for predicting the chance of admissions. This paper attempts to define different regression models and predict students' chances of getting admissions. Prediction is performed using regression models, namely linear regression, ridge regressions, lasso, KNN, and elastic net regression, support vector machine, and few other regression models based on the available data. Further, our study explores two different sampling methods naming random forest and cross-validation sampling. All these regression methods are used to predict students' chance of admitting to the University of their Interest based on their graduate performance. The best regression method is used to predict new unseen data.