Calibrated early-warning models with fairness auditing and selective prediction for course withdrawal risk: Evidence from OULAD
Suhan Wu, Jingyi Duan, Min Luo · 2026
Read Calibrated early-warning models with fairness auditing and selective prediction for course withdrawal risk: Evidence from OULAD by Suhan Wu, Jingyi Duan, Min Luo (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0352867.txt.
Description
Wu, Duan, and Luo studied early warning systems for online courses in a 2026 paper. Such systems flag students who may quit, but reports often skip whether the scores stay fair and trustworthy once schools act on them. The team used records from the Open University and built features from the first four weeks of study.
Nine kinds of prediction models were compared, and a tuned boosting model was kept for deeper checks. Results showed that the cutoff chosen for alerts sharply changed the balance between correct and missed warnings. Fairness also shifted with each policy choice, so the authors argue that alert rules should be set openly, not treated as fixed.
Catalog record
| CREATOR | Suhan Wu, Jingyi Duan, Min Luo |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 66393 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |