Enforcing fairness in binary and multiclass classification
implementation of fair dummies
Supervised link prediction in a social network using graph-based features, Gradient Boosting, and fairness evaluation with Fairlearn.
End-to-End Python implementation of Medina-Olivares et.al's (2026) "findr" framework: a semi-structured credit-risk logit decomposing log-odds into an interpretable linear term and a QR-orthogonalised neural residual, trained with an in-processing Wasserstein fairness penalty and benchmarked on a score-level accuracy-fairness frontier.
This repository was used for my thesis. The goal was to find a biased dataset, and mitigate its bias. That is done under the patients directory. Check the README file for more.
Static fairness audit bench for a real UCI Adult classifier: 6 group-fairness criteria, an EEOC four-fifths check, and a live accuracy-versus-fairness Pareto frontier, no LLM, no API key
To associate your repository with the equalized-odds topic, visit your repo's landing page and select "manage topics."