Evaluating Gender Bias Mitigation and Intersectional Fairness Trade-offs in Educational Prediction Models

SLF–FST: a framework for stress-testing fairness under progressive label bias

Machine learning models are susceptible to reproducing and amplifying structural inequities present in historical data, leading to unjust outcomes in high-stakes domains such as criminal justice, healthcare, employment, and financial services. This paper investigates the relationship between predictive performance and...

The Fairness Illusion? A Cross-Dataset Audit of Accuracy and Demographic Bias in Credit Scoring Based on Machine Learning

Persistent demographic parity disparity among the more complex models is consistent with feature-level bias that no model architecture can resolve, and has direct implications for the less-discriminatory-alternatives framework under US fair lending law and for the high-risk classification of credit scoring AI under the...

Fairness Analysis of Random Forest and Support Vector Machine Models for Predicting Student Academic Performance Based on Demographic and Digital Activities

The application of machine learning models in digital education has become increasingly important for predicting student academic performance and supporting early academic interventions. However, predictive accuracy alone is insufficient if models introduce bias against certain demographic groups. This study presents a...

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

Ensuring that artificial intelligence contributes to sustainable, equitable education requires more than aggregate accuracy—it requires verifying that predictive systems serve all learners fairly, including across geographic regions. We audit a dropout-prediction pipeline built on the Open University Learning Analytics...

When Post-Processing Fairness Constraints Help and When They Harm: Evidence from Eight Cross-Domain Evaluations

FAPE (Fairness Auditing for Production Environments), a four-stage framework evaluating a single post-processing intervention, Fairlearn's ThresholdOptimizer, across eight domain evaluations: criminal justice, income prediction, legal admissions, credit lending, agricultural lending, a multi-domain benchmark corpus, he...

Persona-Aware Evaluation of Cognitive Bias in LLMs: From Benchmark to Applied Decision-Making