IEOM Index
We investigate the application of machine learning techniques to predict student enrollment rates at Turkish foundation universities. In this study, prediction was made with three different algorithms: multiple linear regression, decision tree, and random forest. The model used historically collected data to accurately forecast future enrollment rates and delivers useful findings for optimizations within the area of university institutions. Key factors taken into consideration by foundation universities in Turkey in the process of determining student registrations and capacity of departments were examined. A number of variables affect the success criteria, and benchmarks set to evaluate how well these variables perform. In general, the practical use of machine learning in enrollment estimation was discussed in the project and an enrollment forecast was made for the 2024-2025 academic year. It was emphasized that foundation universities should benefit from machine learning to increase efficiency, optimize resource allocation, and enable relevant managers to make better decisions and develop strategies.
