Education

Inside the Black Box: Detecting and Mitigating Algorithmic Bias across Racialized Groups in College Student-Success Prediction

H. Anahideh, M. P. Ison, et al.

This study by Hadis Anahideh, Matthew P Ison, Anuja Tayal, and Denisa Gándara delves into the profound bias present in college student success prediction models, revealing significant racial disparities, particularly against Black and Hispanic students. The researchers explore multiple machine learning approaches and bias mitigation techniques, ultimately highlighting the challenges in achieving fairness in educational predictions.

00:00

Playback language: English

Index

Abstract

This study investigates bias in college student success prediction models, focusing on racial disparities. Using the Education Longitudinal Study of 2002, the researchers evaluate the fairness of several machine learning models (Random Forest, SVM, Logistic Regression, Decision Tree) and the effectiveness of bias mitigation techniques (reweighting, Disparate Impact Remover, Exponentiated Gradient Reduction, Meta Fair Classifier). They find significant bias against Black and Hispanic students across various fairness metrics (statistical parity, equal opportunity, predictive equality, equalized odds) and limited success in mitigating this bias using existing techniques.

Publisher

International Conference on Educational Data Mining

Published On

Jan 01, 2023

Authors

Hadis Anahideh, Matthew P Ison, Anuja Tayal, Denisa Gándara

Related Publications

Explore these studies to deepen your understanding of the subject.

Linguistics and Languages

Detecting directional forces in the evolution of grammar: A case study of the English perfect with intransitives across EEBO, COHA, and Google Books

S. Okuda, M. Hosaka, et al.

Political Science

Measuring competition between the great powers across Africa and Asia using a measure of relative dispersion in media coverage bias

E. Gooch, S. Goethe, et al.

Environmental Studies and Forestry

Equatorward shift of the boreal summer intertropical convergence zone in Maritime Continent and the impacts on surface black carbon concentration and public health

T. Huang, Y. Gu, et al.

Medicine and Health

Monkeypox outbreaks in the context of the COVID-19 pandemic: Network and clustering analyses of global risks and modified SEIR prediction of epidemic trends

S. Luo, Jg, et al.

Listen, Learn & Level Up

Over 10,000 hours of research content in 25+ fields, available in 12+ languages.

No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.

listen to research audio papers with researchbunny