Should College Dropout Prediction Models Include Protected Attributes?
Open accessThe DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Early identification of college dropouts can provide tremendous value for improving student success and institutional effectiveness, and predictive analytics are increasingly used for this purpose. However, ethical concerns have emerged about whether including protected attributes in these prediction models discriminates against underrepresented student groups and exacerbates existing inequities. We examine this issue in the context of a large U.S. research university with both residential and fully online degree-seeking students. Based on comprehensive institutional records for the entire student population across multiple years (N = 93,457), we build machine learning models to predict student dropout after one academic year of study and compare the overall performance and fairness of model predictions with or without four protected attributes (gender, URM, first-generation student, and high financial need). We find that including protected attributes does not impact the overall prediction performance and it only marginally improves the algorithmic fairness of predictions. These findings suggest that including protected attributes is preferable. We offer guidance on how to evaluate the impact of including protected attributes in a local context, where institutional stakeholders seek to leverage predictive analytics to support student success.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Dwork, C., Hardt, M., Pitassi, T., Reingold, O., & Zemel, R. (2012) · Proceedings of the 3rd Innovations in Theoretical Computer Science Conference · doi:10.1145/2090236.2090255 · Cited by 3,501
Fairness definitions explained
Verma, S., & Rubin, J. (2018) · Proceedings of the International Workshop on Software Fairness · doi:10.1145/3194770.3194776 · Cited by 1,124 · cited 2×
“This definition of fairness with respect to the three metrics correspond to the established notions of overall accuracy equality, equal opportunity and predictive equality, respectively [38].”
BackgroundCourse signals at Purdue: using learning analytics to increase student success
Arnold, K. E., & Pistilli, M. D. (2012) · Proceedings of the 2nd International Conference on Learning Analytics and Knowledge · doi:10.1145/2330601.2330666 · Cited by 987
Predicting academic performance: a systematic literature review
Hellas, A., Ihantola, P., Petersen, A., Ajanovski, V. V., Gutica, M., Hynninen, T., Knutas, A., Leinonen, J., Messom, C., & Liao, S. N. (2018) · Proceedings Companion of the 23rd Annual ACM Conference on Innovation and Technology in Computer Science Education · doi:10.1145/3293881.3295783 · Cited by 355
Kleinberg, J., Ludwig, J., Mullainathan, S., & Rambachan, A. (2018) · AEA Papers and Proceedings · doi:10.1257/pandp.20181018 · Cited by 278
Cited by
Baker, R. S., & Hawn, A. (2022) · International Journal of Artificial Intelligence in Education · doi:10.1007/s40593-021-00285-9 · Cited by 993
Interpretable dropout prediction: towards XAI-based personalized intervention
Nagy, M., & Molontay, R. (2024) · International Journal of Artificial Intelligence in Education · doi:10.1007/s40593-023-00331-8 · Cited by 179
“For the same reasons, Yu et al (2021) also suggest using a cohort-based train-test split.”
Salas-Pilco, S. Z., Xiao, K., & Oshima, J. (2022) · Sustainability · doi:10.3390/su142013572 · Cited by 176
“Improve student performance [39–42,45,47,54,55,59] 9 Encourage student interest in STEM/STEAM [36,37,49–51,58,61] 7 Promote student engagement [44,46,53,56,60] 5 Other advantages [38,43,48,52,57,62] 6”
BackgroundInfluentialGándara, D., Anahideh, H., Ison, M. P., & Picchiarini, L. (2024) · AERA Open · doi:10.1177/23328584241258741 · Cited by 67
“Likewise, using data from a large U.S. research university, Yu et al. (2021) detected disparities in predictions between “underrepre-sented minority” (URM) students and the aggregate group of Asian and White students on three metrics: prediction accuracy; recall, defined as “the proportion of…”
InfluentialSha, L., Rakovic, M., Das, A., Gasevic, D., & Chen, G. (2022) · IEEE Transactions on Learning Technologies · doi:10.1109/tlt.2022.3196278 · Cited by 67
Should learning analytics models include sensitive attributes? Explaining the why
Deho, O. B., Joksimovic, S., Li, J., Zhan, C., Liu, J., & Liu, L. (2023) · IEEE Transactions on Learning Technologies · doi:10.1109/tlt.2022.3226474 · Cited by 35
“On the contrary, other researchers are of the view that sensitive attributes should not be excluded when building LA models [8], [9], [10], [11].”
BackgroundMethodResultInfluential
Metadata
- Authors
- Yu, R., Lee, H., & Kizilcec, R. F.
- Venue
- Proceedings of the Eighth ACM Conference on Learning @ Scale
- Publisher
- ACM
- Published
- 2021-06-08
- Pages
- 91-100
- OpenAlex
- W3166077024
- Cited by
- 95
- References
- 5
- FWCI
- 19.07
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.