Transferring retention prediction models across U.S. colleges without local adaptation degrades performance and fairness, and the paper tests contextual similarity, sequential training, and group-specific thresholds as mitigations.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Fair and Privacy-Aware Transfer Learning for Educational Predictive Modeling: A Case Study on Retention Prediction in Community Colleges
Transferring retention prediction models across U.S. colleges without local adaptation degrades performance and fairness, and the paper tests contextual similarity, sequential training, and group-specific thresholds as mitigations.