Date
Publisher
arXiv
Fairness in artificial intelligence and machine learning (AI/ML) models is becoming critically important, especially as decisions made by these systems impact diverse groups. In education, a vital sector for all countries, the widespread application of AI/ML systems raises specific concerns regarding fairness. Current research predominantly focuses on fairness for individual sensitive features, which limits the comprehensiveness of fairness assessments. This paper introduces FAIREDU, a novel and effective method designed to improve fairness across multiple sensitive features. Through extensive experiments, we evaluate FAIREDU effectiveness in enhancing fairness without compromising model performance. The results demonstrate that FAIREDU addresses intersectionality across features such as gender, race, age, and other sensitive features, outperforming state-of-the-art methods with minimal effect on model accuracy. The paper also explores potential future research directions to enhance further the method robustness and applicability to various machine-learning models and datasets.
Study at a glance
- Question: How can educational AI models be made fairer across multiple personal characteristics without lowering their accuracy?
- Setting and data: Not stated in the abstract
- Method: Computational experiments evaluating a new multiple regression-based fairness method
Why it matters
The widespread application of AI systems in education raises specific concerns regarding fairness for diverse groups. However, current research predominantly focuses on fairness for individual sensitive features, which limits the comprehensiveness of fairness assessments.
Key findings
- In educational applications, a new method successfully improved machine learning fairness across multiple intersecting student traits, including race, gender, and age.
- The method outperformed current leading approaches in reducing bias across overlapping demographic groups.
- The approach enhanced fairness across multiple sensitive features with minimal effect on overall model accuracy.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
