University Student Enrollment Prediction: A Machine Learning Framework

In today's dynamic educational landscape, universities face a tough challenge in accurately predicting student enrollment fluctuations. These fluctuations, driven by factors such as evolving student preferences, economic conditions, and demographic shifts, pose significant hurdles to effective resource allocation, academic planning, and budget management. This research provides a thorough analysis of the use of machine learning models for predicting university student enrollment. In addition, a prediction framework is proposed for researchers to use, along with a summary of the state of the field at the moment. The proposed framework describes three main phases that researchers must follow. The paper also provides a comparative evaluation of multiple prediction models, including classification, and forecasting models, using historical enrollment data. Our results highlight the suggested framework’s effectiveness in enrollment prediction and provide useful information for legislators and administrators at universities.