Predictive and Forecasting Models for University Admissions and Graduation Performance: Leveraging Data Mining Algorithms
Vol 6 No 2 (SI) (2021), Articles
Vol 6 No 2 (SI) (2021)

Predictive and Forecasting Models for University Admissions and Graduation Performance: Leveraging Data Mining Algorithms

Articles
Published December 12, 2021
  • Julius Cesar Mamaril
Julius Cesar Mamaril
PDF

Keywords

Data Mining
Educational Data Mining
University Admissions
Graduation Forecasting
Prediction Algorithms

How to Cite

Mamaril, J. C. (2021). Predictive and Forecasting Models for University Admissions and Graduation Performance: Leveraging Data Mining Algorithms. Southeast Asian Journal of Science and Technology, 6(2 (SI). Retrieved from https://sajst.org/online/index.php/sajst/article/view/275
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Abstract

In recent years, the field of education has seen a surge in the availability of data due to the digitization of various academic processes. This data presents a unique opportunity to harness advanced data mining techniques for enhancing decision-making processes within educational institutions. This research delves into the realm of educational data mining (EDM) by specifically targeting the transition phase of incoming freshmen to their optimal college programs and subsequent graduation performance. By employing cutting-edge relationship discovery and clustering algorithms, this study aims to provide universities with a data-driven approach to streamline the admissions process and facilitate personalized academic pathways for students.

The utilization of historical admission and graduation records as a knowledge base sets the foundation for this research. Through the application of data mining techniques, patterns and trends hidden within the vast dataset can be unveiled, leading to insights that can significantly aid in predicting suitable college programs for incoming students. The predictive power of these techniques can empower academic advisors and university administrators to make well-informed decisions while considering factors such as students' academic backgrounds, interests, and potential career paths.

The research not only focuses on predicting appropriate college programs but also extends its scope to forecast the final graduation grades of students. By analyzing the historical data, this study aims to develop models that can accurately predict students' academic performance based on their selected programs and individual attributes. This predictive capability has the potential to assist universities in identifying students who might be at risk of underperforming and proactively providing them with targeted support services, ultimately improving their chances of successful graduation.

PDF

Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.