Predicting Chance of Admission: A Machine Learning Perspective

Today’s dynamic higher education climate makes it harder to get into a Master’s degree. Our study employs machine learning algorithms to develop a prediction model that helps people make decisions and select universities that align with their academic objectives in order to get over this uncertainty problem. This study is based on an extensive data set that comprises the academic profiles of 400 students.The original dataset encountered a significant challenge in the application of machine learning techniques, particularly concerning the train-test split for predictive modelling, which made it difficult to assess the model’s performance on unseen data. Furthermore, the response variable was not normally distributed, which is a prerequisite for fitting linear regression with continuous data values. Augmented with 1600 more entries, our dataset guarantees a more thorough assessment of prediction models, alleviating constraints and strengthening the validity of our conclusions while preserving the correlation between the characteristics’ underlying pattern. By analyzing MSE and R-squared values, we compare model performances across a variety of institutional kinds. Our study contributes valuable insights about predictive modeling in graduate admissions.