MESD: Detecting and Mitigating Procedural Bias in Intersectional Groups
#MESD #procedural bias #intersectional groups #fairness #algorithmic bias #mitigation #decision-making
📌 Key Takeaways
- MESD is a method for detecting procedural bias in intersectional groups.
- It focuses on mitigating bias in decision-making processes.
- The approach addresses fairness across multiple demographic dimensions.
- It aims to improve equity in algorithmic and human-driven systems.
📖 Full Retelling
arXiv:2603.13452v1 Announce Type: new
Abstract: Research about bias in machine learning has mostly focused on outcome-oriented fairness metrics (e.g., equalized odds) and on a single protected category. Although these approaches offer great insight into bias in ML, they provide limited insight into model procedure bias. To address this gap, we proposed multi-category explanation stability disparity (MESD), an intersectional, procedurally oriented metric that measures the disparity in the qualit
🏷️ Themes
Bias Detection, Fairness Algorithms
Entity Intersection Graph
No entity connections available yet for this article.
Original Source
arXiv:2603.13452v1 Announce Type: new
Abstract: Research about bias in machine learning has mostly focused on outcome-oriented fairness metrics (e.g., equalized odds) and on a single protected category. Although these approaches offer great insight into bias in ML, they provide limited insight into model procedure bias. To address this gap, we proposed multi-category explanation stability disparity (MESD), an intersectional, procedurally oriented metric that measures the disparity in the qualit
Read full article at source