Toward Sustainable and Equitable AI in Education Through a Regional Fairness Audit of Dropout Prediction Using the OULAD Dataset

Short summary

A fairness audit of an AI dropout prediction system on the OULAD dataset found significant performance disparities across geographic regions, with recall rates ranging from 0.55 in Wales to 0.80 in the West Midlands, indicating a potential bias against students in certain areas.

AI-generated from the title and abstract; the full text is not read.