Logistic regression performs poorly (mean accuracy 0.4243) and SVM moderately (0.7374) on physiological exam-outcome prediction¶

Claim · All claims
Evidence · 1 study (2 entries) · associational r1 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly

Subclaims¶

q2 i? Logistic regression exhibited the lowest mean accuracy (0.4243) of all models, struggling with the dataset's non-linear and multivariate complexity. → Lala Yamazaki and Ramchandra Rimal 2026 q2 i? SVM achieved moderate mean accuracy of 0.7374 on the same task. → Lala Yamazaki and Ramchandra Rimal 2026 (2)

Evidence¶

Lala Yamazaki and Ramchandra Rimal 2026¶

Lala Yamazaki and Ramchandra Rimal. (2026). Leveraging Physiological Signals to Predict Exam Outcomes with Machine Learning. https://arxiv.org/abs/2606.14960 doi:10.48550/arxiv.2606.14960

q2 · i? · associational · r1

Test-set comparison of tuned models; the article reports logistic regression "demonstrates the lowest performance with mean metrics below 0.42" (Table 5: accuracy 0.4243 ± 0.0000), attributing this to inability to capture complex interactions.

"Logistic regression demonstrates the lowest performance with mean metrics below 0.42, making it ill-suited for handling the dataset's complexity."

Lala Yamazaki and Ramchandra Rimal 2026 (2)¶

Lala Yamazaki and Ramchandra Rimal. (2026). Leveraging Physiological Signals to Predict Exam Outcomes with Machine Learning. https://arxiv.org/abs/2606.14960

q2 · i? · associational · r1

Same test-set comparison; the article reports SVM "exhibit moderate performance with mean metrics around 0.74" (Table 5: accuracy 0.7374 ± 0.0000, deterministic across runs).

"Meanwhile, SVM exhibit moderate performance with mean metrics around 0.74."

Discussion¶

Related Claims¶

• Deep learning models (LSTM, GRU, transformer) achieve high and comparable accuracy (0.90–0.93) on physiological exam-outcome prediction — related
• Simple classifiers (Logistic Regression, Naive Bayes) outperformed tree-based models on this small dataset — reports the opposite
• Logistic Regression and linear-kernel SVM achieve the highest accuracy (99%) among five classifiers predicting student withdrawal/cancellation at SISTC — related
• Using all collected physiological features improves exam-grade prediction accuracy to 96% over the 80% achieved by prior EDA-only analyses — related
• Random forest achieves the highest mean test accuracy (0.9590) of all models compared for predicting exam grade categories from physiological signals — related
• Machine learning methods outperformed logistic regression in classification accuracy across reviewed studies — reports the opposite
• Pairwise statistical tests confirm random forest's performance differences from other models are statistically significant (p < 0.05) — related
• Decision trees achieve competitive accuracy with black-box models (LR, RF, SVM), which performed slightly better but lack interpretability — related