Predicting Student Success in Higher Education: A Data-Informed Analysis of Key Institutional Variables
AIR Professional File · 2026 · (Spring 2026)
DOI: 10.34315/apf1822026 ↗Kurz gefasst
Fachartikel in der Zeitschrift AIR Professional File, 2026. Verfasst von Prabesh Shrestha und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Higher education institutions increasingly rely on data-informed strategies to support student success, yet identifying the most impactful variables remains a challenge. This study integrates insights from existing literature with institutional data from a Midwestern, profession-focused associate degree– granting higher education institution to evaluate predictors of academic success, defined as the successful completion of all registered courses in a semester. Using Random Forest and generalized regression models, the analysis reveals that academic standing, early alert indicators (flags), and positive reinforcement (kudos) are the most consistent and significant predictors of student success. Financial aid and advisor contact show moderate, context-dependent effects, while demographic and enrollment characteristics, such as gender, age, and first-generation status, exhibit limited predictive power. These findings underscore the importance of proactive academic support, timely interventions, and recognition systems. Institutions can enhance student success by prioritizing early alerts, targeted advising, and financial support for their students.
Zitieren
APA
Shrestha, P., & Xu, X. (2026). Predicting Student Success in Higher Education: A Data-Informed Analysis of Key Institutional Variables. AIR Professional File. https://doi.org/10.34315/apf1822026
Vancouver
Shrestha P, Xu X. Predicting Student Success in Higher Education: A Data-Informed Analysis of Key Institutional Variables. AIR Professional File. 2026. doi:10.34315/apf1822026
BibTeX
@article{Shrestha2026,
author = {Shrestha, Prabesh and Xu, Xiaowei},
title = {Predicting Student Success in Higher Education: A Data-Informed Analysis of Key Institutional Variables},
journal = {AIR Professional File},
year = {2026},
number = {Spring 2026},
doi = {10.34315/apf1822026}
}
EUVIMED