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

TL;DR

This paper introduces a post-processing fairness method based on the MADD metric for predictive student models, aiming to enhance fairness without sacrificing accuracy in educational predictions.

Contribution

It develops a novel post-processing approach utilizing the MADD fairness metric specifically for predictive student models in education.

Findings

Improved fairness in student success predictions

Maintained accuracy while enhancing fairness

Validated on real-world and simulated educational data

Abstract

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 .