Auflistung nach Schlagwort "Fair AI"
1 - 2 von 2
Treffer pro Seite
Sortieroptionen
- KonferenzbeitragThe Effect of Adversarial Debiasing on Model Performance(INFORMATIK 2023 - Designing Futures: Zukünfte gestalten, 2023) Götte, GesaThis paper explores the effect of adversarial debiasing on the performance of machine learning models. As concerns about fairness in algorithmic decision-making grow, techniques for detecting and mitigating biases in ML models have been developed. However, there is a trade-off between fairness and model performance. This study investigates the impact of using adversarial debiasing on model performance in different scenarios of potential sampling biases and target distributions. Simulated data with varying structural and sampling parameters is used to evaluate the models’ performance. The results show that while adversarial debiasing can lead to significant improvements in certain scenarios, it can also result in impairments or no significant difference in performance compared to the normal models.
- ZeitschriftenartikelThe Cost of Fairness in AI: Evidence from E-Commerce(Business & Information Systems Engineering: Vol. 64, No. 3, 2022) Zahn, Moritz; Feuerriegel, Stefan; Kuehl, NiklasContemporary information systems make widespread use of artificial intelligence (AI). While AI offers various benefits, it can also be subject to systematic errors, whereby people from certain groups (defined by gender, age, or other sensitive attributes) experience disparate outcomes. In many AI applications, disparate outcomes confront businesses and organizations with legal and reputational risks. To address these, technologies for so-called “AI fairness�? have been developed, by which AI is adapted such that mathematical constraints for fairness are fulfilled. However, the financial costs of AI fairness are unclear. Therefore, the authors develop AI fairness for a real-world use case from e-commerce, where coupons are allocated according to clickstream sessions. In their setting, the authors find that AI fairness successfully manages to adhere to fairness requirements, while reducing the overall prediction performance only slightly. However, they find that AI fairness also results in an increase in financial cost. Thus, in this way the paper’s findings contribute to designing information systems on the basis of AI fairness.