Baseline LR and XGBoost models achieve comparable predictive performance on OULAD, with XGBoost slightly higher AUC-ROC¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person · recheck by 2028: tool and model accuracy changes quickly

Subclaims¶

q2 i? LR achieved 75% accuracy (AUC-ROC 0.8328) and XGBoost 74% accuracy (AUC-ROC 0.8433) on the binary pass/fail prediction task. → Raymond A. Opoku 2025

Evidence¶

Raymond A. Opoku 2025¶

Raymond A. Opoku, Bo Pei and Wanli Xing. (2025). Unveiling Accuracy-Fairness Trade-Offs: Investigating Machine Learning Models in Student Performance Prediction. Journal of Learning Analytics 12(2). https://doi.org/10.18608/jla.2025.8543

q2 · i? · design · r2

Baseline evaluation of LR and XGBoost on OULAD using 10-fold nested cross-validation (Tables 2-3, Figure 5). The article reports LR accuracy of 75% with AUC-ROC 0.8328 and XGBoost accuracy of 74% with AUC-ROC 0.8433. AUC/accuracy values are not standardized effect sizes.

"The AUC-ROC score for the XGBoost model is 0.8433, which is slightly higher than that of the LR model, indicating marginally better performance in distinguishing between the pass and fail classes."

Discussion¶

Related Claims¶

• Standard ML models predicting student pass/fail from VLE data exhibit biased true-positive rates across demographic subgroups — related
• CatBoost achieved the best classification performance among tested algorithms for predicting course completion risk (F-measure .77, accuracy 78%, AUC .87) — related
• Gradient boosting and extreme gradient boosting are the highest-performing classifiers for predicting enrollment, with balanced accuracy 0.91, F-score 0.88 and AUC 0.96 — related
• Percentile heuristics transferred from health behavior systematically overpredict weekly K-12 engagement and underperform XGBoost by 20-30% — related
• Question and observed-coverage features retrospectively predict high-divergence questions with AUC 0.774, but the model is not validated for new-query routing — related
• Models can predict best-fit majors from student records, not only pass or fail within a chosen major, enabling cross-program success questions — related
• Integer-programming recourse generates compact, model-valid, SHACL-conformant intervention plans at scale on OULAD — related
• Supplementary nonlinear models yield only modest AUC gains over the calibrated logistic baseline — related
• A calibrated logistic-regression model predicts next-assessment pass/fail strongly on OULAD at both decision horizons — related
• Explainable models including logistic regression, kNN and a Bernoulli Mixture Model all reach around 78% accuracy in predicting question-level pass/fail, with well-calibrated probabilities — related
• Machine learning methods outperformed logistic regression in classification accuracy across reviewed studies — reports the opposite
• Decision trees achieve competitive accuracy with black-box models (LR, RF, SVM), which performed slightly better but lack interpretability — related
• Boosting models (XGBoost) achieved the highest predictive accuracy among the compared ML models, while logistic regression showed the lowest — reports the opposite