A Fair Post-Processing Method based on the MADD Metric for Predictive Student Models
This work addresses fairness issues in educational predictive models, which is important for students and educators, but it is incremental as it builds on existing metrics and post-processing techniques.
The authors tackled the problem of algorithmic unfairness in predictive student models by developing a post-processing method based on the Model Absolute Density Distance (MADD) metric to improve fairness while preserving accuracy, and they successfully tested it on predicting student success in an online course using simulated and real-world data.
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 .