Machine learning models using weekly SRL-aligned digital trace indicators can predict at-risk students early within courses but lose accuracy and calibration when applied across institutions with different at-risk base rates.
For XGBoost, the maximum tree depth was varied on3,4,...,10and the minimum child weight was between 1 and 10
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Cross-Course Generalizability of SRL-Aligned Predictive Models Using Digital Learning Traces
Machine learning models using weekly SRL-aligned digital trace indicators can predict at-risk students early within courses but lose accuracy and calibration when applied across institutions with different at-risk base rates.