Towards Equity and Algorithmic Fairness in Student Grade Prediction

TL;DR

This paper evaluates methods to improve fairness and equity in student grade prediction models, proposing strategies that reduce racial bias and enhance predictive accuracy for underserved groups in higher education.

Contribution

It introduces empirical evaluation of fairness strategies, including adversarial learning and sampling techniques, to address racial bias and improve equity in educational AI systems.

Findings

Adversarial learning combined with grade label balancing achieved the fairest results.

Sampling underserved groups inversely to their historic outcomes improved predictive performance.

Frameworks developed help institutions balance fairness and accuracy in AI-driven education.

Abstract

Equity of educational outcome and fairness of AI with respect to race have been topics of increasing importance in education. In this work, we address both with empirical evaluations of grade prediction in higher education, an important task to improve curriculum design, plan interventions for academic support, and offer course guidance to students. With fairness as the aim, we trial several strategies for both label and instance balancing to attempt to minimize differences in algorithm performance with respect to race. We find that an adversarial learning approach, combined with grade label balancing, achieved by far the fairest results. With equity of educational outcome as the aim, we trial strategies for boosting predictive performance on historically underserved groups and find success in sampling those groups in inverse proportion to their historic outcomes. With AI-infused technology supports increasingly prevalent on campuses, our methodologies fill a need for frameworks to consider performance trade-offs with respect to sensitive student attributes and allow institutions to instrument their AI resources in ways that are attentive to equity and fairness.