Random forest feature importance identifies EDA, ACC, and TEMP as the top three physiological predictors of exam outcomes¶

Claim · All claims
Evidence · 1 study · 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? Feature importance analysis of the best-performing random forest model ranked electrodermal activity, accelerometer data, and skin temperature as the top three predictors. → Lala Yamazaki and Ramchandra Rimal 2026

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

Feature importance analysis of the selected random forest model (Fig. 9 shows longer bars indicating greater contribution); the article reports it "revealed EDA, ACC, and TEMP as the top three predictors for exam outcomes".

"Its feature importance analysis revealed EDA, ACC, and TEMP as the top three predictors for exam outcomes, providing additional insights for practical application in cognitive performance assessment."

Discussion¶

Related Claims¶

• 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
• Deep learning models (LSTM, GRU, transformer) achieve high and comparable accuracy (0.90–0.93) on physiological exam-outcome prediction — related