A Fair Post-Processing Method based on the MADD Metric for Predictive Student Models

Mélina Verger (1) , Chunyang Fan (1) , Sébastien Lallé (1) , François Bouchet (1) , Vanda Luengo (1)

1 MOCAH - Modèles et Outils en ingénierie des Connaissances pour l'Apprentissage Humain

Predictive student models are increasingly used in learning environments. However, due to the rising social impact of their usage, it is now all the more important for these models to be both sufficiently accurate and fair in their predictions. To evaluate algorithmic fairness, a new metric has been developed in education, namely the Model Absolute Density Distance (MADD). This metric enables us to measure how different a predictive model behaves regarding two groups of students, in order to quantify its algorithmic unfairness. In this paper, we thus develop a post-processing method based on this metric, that aims at improving the fairness while preserving the accuracy of relevant predictive models' results. We experiment with our approach on the task of predicting student success in an online course, using both simulated and real-world educational data, and obtain successful results. Our source code and data are in open access at https://github.com/melinaverger/MADD.

Mots clés: Algorithmic fairness; Mitigation; Success prediction

Domaines: Intelligence artificielle [cs.AI]; Environnements Informatiques pour l'Apprentissage Humain; Ordinateur et société [cs.CY]

Mélina Verger, Chunyang Fan, Sébastien Lallé, François Bouchet, Vanda Luengo. A Fair Post-Processing Method based on the MADD Metric for Predictive Student Models. 1st International Tutorial and Workshop on Responsible Knowledge Discovery in Education (RKDE 2023) at ECML PKDD 2023, Sep 2023, Turino, Italy. ⟨hal-04345451⟩