EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable Machine Learning for Student Performance Prediction

Yu Lu, Avinash Shashikala Rajendra, Jun Zhang, Tian Zhao

AI in Education · 01.06.2026 · 2 (2) · 17

DOI: 10.3390/aieduc2020017 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AI in Education, online erschienen am 01.06.2026. Verfasst von Yu Lu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Wisconsin–Milwaukee (UWM) Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Early identification of at-risk students is crucial for timely pedagogical intervention. Determining which assessments instructors should prioritize is complicated by the fact that different eXplainable-AI (XAI) methods can produce conflicting rankings for the same predictive model. We develop a framework combining a sequential GRU model with two complementary XAI techniques, Gradient SHAP (attribution) and DiCE (counterfactuals), and evaluate it in a foundational Data Structures and Algorithms course. The framework produces predictions and explanations for every prefix length throughout the semester and quantifies inter-method agreement and intra-method stability using three disagreement metrics. Intersecting the top-k features identified by both methods isolates a compact subset of assessments whose predictive role is confirmed across two fundamentally different explanation mechanisms. We interpret this cross-method agreement as a heuristic that increases confidence in identified features relative to single-method results, though not as evidence of causal validity. For individual students, the framework uses the intersection of the two types of explanations when it is non-empty; otherwise, the instructor chooses between SHAP’s diagnostic view and DiCE’s prescriptive view, with an optional check against the top-k list. The resulting guidance is less susceptible to method-specific biases than analyses relying on a single method.

Förderung

  • University of Wisconsin–Milwaukee (UWM) Foundation

Zitieren

APA

Lu, Y., Rajendra, A. S., Zhang, J., & Zhao, T. (2026). Explainable Machine Learning for Student Performance Prediction. AI in Education, 2(2), 17. https://doi.org/10.3390/aieduc2020017

Vancouver

Lu Y, Rajendra AS, Zhang J, Zhao T. Explainable Machine Learning for Student Performance Prediction. AI in Education. 2026;2(2):17. doi:10.3390/aieduc2020017

BibTeX
@article{Lu2026,
  author = {Lu, Yu and Rajendra, Avinash Shashikala and Zhang, Jun and Zhao, Tian},
  title = {Explainable Machine Learning for Student Performance Prediction},
  journal = {AI in Education},
  year = {2026},
  volume = {2},
  number = {2},
  pages = {17},
  doi = {10.3390/aieduc2020017}
}
Kostenlos starten →