Analytical Study Forecasting Students Using Random Forest and Linear Regression Algorithms

Forecasting new student admissions essential for higher education institutions as it helps them plan for staffing and budgetary needs. Accurate predictions are difficult due to factors like economic conditions, government policies, and University competition. This study aims to analysis forecasting at Nasional university using Random Forest and Linear Regression algorithms. By examining historical admission data, the research seeks to identify key factors influencing the number of accepted students. Methodology involves collecting data from past admissions and applying both Random Forest and Linear Regression to compare their performance. Preliminary results, based on parameters such as application form purchases from 2015 to 2023, form prices, accreditation, and leading study programs, suggest that Random Forest offers more stable and realistic predictions. Analysis for MAE, MSE, RMSE, MAPE, MAD suggests that Linear Regression is more accurate for this data. predicts closer to actual values with lower overall errors. This makes Linear Regression preferable as it provides more reliable predictions with less deviation compared to Random Forest. Looking at admissions forecasts for the next 5 years, Random Forest predicts a steady decrease from 4224 in 2024 to 4129 in 2028. In contrast, Linear Regression suggests a stable trend with slight annual dips, going from 4954 in 2024 to 4941 in 2028. Therefore, Linear Regression is a more stable and realistic choice compared to Random Forest for this forecasting task in this research.