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

Colleges and universities are increasingly turning to algorithms that predict college-student success to inform various decisions, including those related to admissions, budgeting, and student-success interventions. Because predictive algorithms rely on historical data, they capture societal injusti...

Full description

Saved in:
Bibliographic Details
Main Authors: Denisa Gándara, Hadis Anahideh, Matthew P. Ison, Lorenzo Picchiarini
Format: Article
Language:English
Published: SAGE Publishing 2024-06-01
Series:AERA Open
Online Access:https://doi.org/10.1177/23328584241258741
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832584924189687808
author Denisa Gándara
Hadis Anahideh
Matthew P. Ison
Lorenzo Picchiarini
author_facet Denisa Gándara
Hadis Anahideh
Matthew P. Ison
Lorenzo Picchiarini
author_sort Denisa Gándara
collection DOAJ
description Colleges and universities are increasingly turning to algorithms that predict college-student success to inform various decisions, including those related to admissions, budgeting, and student-success interventions. Because predictive algorithms rely on historical data, they capture societal injustices, including racism. In this study, we examine how the accuracy of college student success predictions differs between racialized groups, signaling algorithmic bias. We also evaluate the utility of leading bias-mitigating techniques in addressing this bias. Using nationally representative data from the Education Longitudinal Study of 2002 and various machine learning modeling approaches, we demonstrate how models incorporating commonly used features to predict college-student success are less accurate when predicting success for racially minoritized students. Common approaches to mitigating algorithmic bias are generally ineffective at eliminating disparities in prediction outcomes and accuracy between racialized groups.
format Article
id doaj-art-497a211e6ed64c0e922aac3776b0ee7a
institution Kabale University
issn 2332-8584
language English
publishDate 2024-06-01
publisher SAGE Publishing
record_format Article
series AERA Open
spelling doaj-art-497a211e6ed64c0e922aac3776b0ee7a2025-01-27T09:03:23ZengSAGE PublishingAERA Open2332-85842024-06-011010.1177/23328584241258741Inside the Black Box: Detecting and Mitigating Algorithmic Bias Across Racialized Groups in College Student-Success PredictionDenisa GándaraHadis AnahidehMatthew P. IsonLorenzo PicchiariniColleges and universities are increasingly turning to algorithms that predict college-student success to inform various decisions, including those related to admissions, budgeting, and student-success interventions. Because predictive algorithms rely on historical data, they capture societal injustices, including racism. In this study, we examine how the accuracy of college student success predictions differs between racialized groups, signaling algorithmic bias. We also evaluate the utility of leading bias-mitigating techniques in addressing this bias. Using nationally representative data from the Education Longitudinal Study of 2002 and various machine learning modeling approaches, we demonstrate how models incorporating commonly used features to predict college-student success are less accurate when predicting success for racially minoritized students. Common approaches to mitigating algorithmic bias are generally ineffective at eliminating disparities in prediction outcomes and accuracy between racialized groups.https://doi.org/10.1177/23328584241258741
spellingShingle Denisa Gándara
Hadis Anahideh
Matthew P. Ison
Lorenzo Picchiarini
Inside the Black Box: Detecting and Mitigating Algorithmic Bias Across Racialized Groups in College Student-Success Prediction
AERA Open
title Inside the Black Box: Detecting and Mitigating Algorithmic Bias Across Racialized Groups in College Student-Success Prediction
title_full Inside the Black Box: Detecting and Mitigating Algorithmic Bias Across Racialized Groups in College Student-Success Prediction
title_fullStr Inside the Black Box: Detecting and Mitigating Algorithmic Bias Across Racialized Groups in College Student-Success Prediction
title_full_unstemmed Inside the Black Box: Detecting and Mitigating Algorithmic Bias Across Racialized Groups in College Student-Success Prediction
title_short Inside the Black Box: Detecting and Mitigating Algorithmic Bias Across Racialized Groups in College Student-Success Prediction
title_sort inside the black box detecting and mitigating algorithmic bias across racialized groups in college student success prediction
url https://doi.org/10.1177/23328584241258741
work_keys_str_mv AT denisagandara insidetheblackboxdetectingandmitigatingalgorithmicbiasacrossracializedgroupsincollegestudentsuccessprediction
AT hadisanahideh insidetheblackboxdetectingandmitigatingalgorithmicbiasacrossracializedgroupsincollegestudentsuccessprediction
AT matthewpison insidetheblackboxdetectingandmitigatingalgorithmicbiasacrossracializedgroupsincollegestudentsuccessprediction
AT lorenzopicchiarini insidetheblackboxdetectingandmitigatingalgorithmicbiasacrossracializedgroupsincollegestudentsuccessprediction