Higher Education Institution (HEI) Enrollment Forecasting Using Data Mining Technique
P Adeline
Abstract
Prediction plays a vital role used for strategic and tactical decision-making undertaking sthat pave the way for efficient and effective management. Prediction is beneficial in HEI mining in its continued quest to study on the historical, current, and the continuance data relationships for particular situations from an educational context. This paper employed the famous ARIMA(p,d,q) model in forecasting HEI general student enrollment count for S.Y. 2019-2020 to S.Y. 2024-2025 using the university's overall enrollment data for S.Y. 2011-2012 to 2018-2019. Different p,d,q values were tested, and the model with the lowest Akaike Information Criterion (AIC) value was used for prediction. The simulation result showed that ARIMA(0,2,1) model appeared to be the statistically appropriate model to forecast enrollment in the university. The forecast showed an increasing trend in enrollment for the succeeding school years. Future researchers may utilize other data mining algorithms and consider the specific prediction of enrollment counts per colleges for better enrollment trend analysis and knowledge extraction.