Automated Prediction Model for Graduate Admission in Foreign Universities

The objective of this study is to assess how various factors, including GRE Score, TOEFL Score, University Rating, Statement of Purpose (SOP), Letter of Recommendation (LOR), CGPA (Cumulative Grade Point Average), and Research Experience, influence the likelihood of admission to graduate programs at international universities. The article also proposes to develop an automated prediction model for graduate admissions in foreign universities. A Descriptive-correlation research method is used in the present study. The Graduate Admissions dataset consists of 500 instances and 8 attributes collected from the Kaggle platform. The dataset under examination comprises a range of attributes, including Serial Number, GRE Score, TOEFL Score, University Rating, Statement of Purpose (SOP), Letter of Recommendation (LOR), CGPA (Cumulative Grade Point Average), Research Experience, and the Probability of Admission. Predictive modeling for graduate admissions using machine learning is used to help graduates procure admission into the foreign universities. A Statistical tool like the Stepwise Regression Analysis technique is applied to predict the chance of admission to a foreign university based on the graduate admission dataset. The results revealed that a good CGPA along with the research experience and GRE score is essential. Good TOEFL and LOR boost the chance of admission. The proposed web application would help the students to predict their chances of getting admitted. This study holds significance for educational policy development and sheds light on potential avenues for future research. It underscores the potential of leveraging predictive models to attract highly qualified students for admissions. The present model can be added to the existing multiple models to prove the accuracy of the prediction of students getting admitted to graduate programs in foreign universities.