Sustainability Research in Higher Education: New Findings in Grade Prediction Modeling

Strategic Insights -

Researchers at the University of West Attica, in Athens, Greece, have been studying the impact of the COVID-19 pandemic on higher education and exploring new methods for predicting student performance in hybrid learning environments. According to the study, since mid-March 2020, universities have been implementing hybrid learning models, combining distance and face-to-face learning. The study aimed to identify and quantify the main factors affecting mechanical engineering student performance and develop a generalized linear autoregressive (GLAR) model to predict student grades in online learning situations in hybrid environments.

Key Takeaways:

  • The study identified 30 variables affecting mechanical engineering student performance in online learning, which were evaluated in blended learning spaces.
  • A refined version of the GLAR model predicts student grades to within ±1 with a success rate of 63.70%, making it 28.08% more accurate than the original model created in 2020-2021.
  • The methodology presented is applicable to all aspects of the academic process, including students, instructors, and decision-makers.
  • The study focused on students whose grade predictions were underestimated and who failed, providing insights into strategies for improvement.
  • The research emphasizes the importance of learning from the past years of health crisis to build a post-COVID-19 university education.
  • The study involved collaboration between researchers from the University of West Attica, including Zoe Kanetaki, Constantinos Stergiou, Georgios Bekas, Sebastien Jacques, Christos Troussas, Cleo Sgouropoulou, and Abdeldjalil Ouahabi.

Statistics:

  • The original model's predictive power was about 35.62% lower than the refined model.
  • The refined model's success rate of 63.70% represents an increase of 28.08% compared to the original model.
  • The model predicts grades to within ±1 with a success rate of 63.70%, indicating a high level of accuracy.
  • The study focused on mechanical engineering students, but the methodology can be applied to other fields of study as well.

Sources:

  • Sustainability (journal)

MDPI AG (publisher)

doi: https://doi-org.sdpl.idm.oclc.org/10.3390/su14095205

  • Respiratory Therapeutics Week (newspaper)

NewsRx LLC (publisher)