EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Metrics and Algorithms for Identifying and Mitigating Bias in AI Design: A Counterfactual Fairness Approach

Dongsoo Moon, Seongjin Ahn

IEEE Access · 2025 · 13 · 59118-59129

DOI: 10.1109/access.2025.3556082 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2025. Verfasst von Dongsoo Moon und 1 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid advancements in artificial intelligence (AI) have revolutionized industries such as healthcare, finance, and education. However, these advancements have also intensified ethical concerns regarding bias, fairness, and accountability in AI systems. Traditional fairness evaluation methods primarily focus on dataset-level biases, overlooking biases arising from model decision-making processes. This study introduces a novel framework for identifying, evaluating, and mitigating biases in AI models using counterfactual fairness, a robust approach that simulates alternative outcomes to minimize discriminatory effects. The proposed methodology integrates fairness-aware data preprocessing, feature selection, and model optimization strategies, ensuring equitable treatment across demographic groups. To validate the framework, we conducted empirical experiments using random forest and eXtreme Gradient Boosting models on the xAPI-Edu-Data dataset. Our results demonstrate significant improvements in demographic parity and equal opportunity fairness metrics while maintaining high predictive performance. Furthermore, comparative analysis with existing bias mitigation techniques confirms that our approach effectively reduces bias propagation in AI decision-making processes. By incorporating counterfactual fairness into AI design, this study provides a scalable and adaptable solution for ensuring ethical AI deployments aligned with regulatory standards.

Zitieren

APA

Moon, D., & Ahn, S. (2025). Metrics and Algorithms for Identifying and Mitigating Bias in AI Design: A Counterfactual Fairness Approach. IEEE Access, 13, 59118-59129. https://doi.org/10.1109/access.2025.3556082

Vancouver

Moon D, Ahn S. Metrics and Algorithms for Identifying and Mitigating Bias in AI Design: A Counterfactual Fairness Approach. IEEE Access. 2025;13:59118-59129. doi:10.1109/access.2025.3556082

BibTeX
@article{Moon2025,
  author = {Moon, Dongsoo and Ahn, Seongjin},
  title = {Metrics and Algorithms for Identifying and Mitigating Bias in AI Design: A Counterfactual Fairness Approach},
  journal = {IEEE Access},
  year = {2025},
  volume = {13},
  pages = {59118--59129},
  doi = {10.1109/access.2025.3556082}
}
Kostenlos starten →