A DYNAMIC AI FRAMEWORK PREDICTS UNIVERSITY STUDENT PERFORMANCE FROM FORMATIVE DATA WITH HIGH ACCURACY.
The purpose of this study is to investigate the feasibility of employing artificial intelligence (AI) techniques to forecast the ultimate academic performance of college students by utilizing formative assessment data. The dataset consisted of 734 male students who were enrolled in an undergraduate...
| Publicado en: | Scientific Culture Vol. 11; no. 4; pp. 1171 - 1184 |
|---|---|
| Autor principal: | |
| Formato: | Artículo |
| Publicado: |
University of the Aegean
2025
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=191047185&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 191047185 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 24080071 I6HU jtl: Scientific Culture issn: 24080071 maglogo: N pubinfo: dt: 2025 vid: 11 iid: 4 pid: 47715 pub: University of the Aegean artinfo: ui: 191047185 10.5281/zenodo.11042591 ppf: 1171 ppct: 13 formats: tig: atl: A DYNAMIC AI FRAMEWORK PREDICTS UNIVERSITY STUDENT PERFORMANCE FROM FORMATIVE DATA WITH HIGH ACCURACY. aug: au: Aljubaily, Hesham Yahya Ali affil: College of Social Sciences, Department of Psychology, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, Saudi Arabia su: Artificial intelligence Prediction models Random forest algorithms Longitudinal method Ridge regression (Statistics) Academic achievement Formative evaluation sug: subj: Artificial intelligence Prediction models Random forest algorithms Longitudinal method Ridge regression (Statistics) Academic achievement Formative evaluation keyword: Academic Performance Prediction Artificial Intelligence Educational Data Mining Formative Assessment Random Forest Ridge Regression ab: The purpose of this study is to investigate the feasibility of employing artificial intelligence (AI) techniques to forecast the ultimate academic performance of college students by utilizing formative assessment data. The dataset consisted of 734 male students who were enrolled in an undergraduate psychological statistics course at Imam Mohammad ibn Saud Islamic University. The records were collected over the course of six consecutive semesters. Attendance, participation in in-class activities, homework assignments, and midterm examinations were all important aspects of the assessment process. The application of an ensemble learning technique known as Random Forest resulted in a high degree of prediction accuracy (R2 = 0.9132), which led to the determination that the midterm was the most influential predictor. In addition, a regularized regression model known as Ridge Regression was utilized in order to validate the accuracy of the prediction in comparison to the actual student results. This model achieved 96.2% alignment within the estimated prediction intervals, so proving a significant real-world applicability. Further investigation into the relationship between cumulative semester data and prediction performance was carried out in this study, which revealed that the accuracy of the model improved as more longitudinal information was incorporated. It is because of this that the importance of data accumulation in improving the dependability of predictions over time is strengthened. In comparison to previous research, this study is distinguished by the incorporation of numerous modeling methodologies, the utilization of actual student performance data, and the conducting of analysis at the semester level. In addition to providing scalable and accurate tools for educational decision-making and early intervention frameworks, the findings offer empirical support for the adoption of AI-based predictive models in academic analytics. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y dt: @attributes: year: 2025 holdings: @attributes: islocal: N |
|---|