Abstract
Predictive models are increasingly being deployed in social and behavioral applications in support of decision making that directly affects people’s lives. Given such high stakes, it is important to develop models with interpretable and defensible features, with decisions that are unbiased toward historically marginalized groups. In this work we investigate the use of nonnegative matrix factorization (NMF) for generating interpretable features in an educational setting, combined with a standard bias mitigation algorithm for training predictive models. Our application in this work is predicting enrollment in STEM degrees, and improving fairness of our models through bias mitigation. We perform our experiments on the High School Longitudinal Study of 2009, and evaluate our results using both objective metrics and subjective interpretation of the NMF factors, or behavioral phenotypes. Our empirical results from these experiments suggest that NMF combined with bias mitigation can potentially be used to improve fairness measures while simultaneously aiding in interpretability.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Barocas, S., Selbst, A.D.: Big data’s disparate impact. Calif. L. Rev. 104, 671 (2016)
Beede, D.N., Julian, T.A., Langdon, D., McKittrick, G., Khan, B., Doms, M.E.: Women in STEM: a gender gap to innovation. Economics and Statistics Administration Issue Brief (04–11) (2011)
Bellamy, R.K.E., et al.: AI Fairness 360: an extensible toolkit for detecting, understanding, and mitigating unwanted algorithmic bias, October 2018. https://arxiv.org/abs/1810.01943
Berry, M.W., Browne, M., Langville, A.N., Pauca, V.P., Plemmons, R.J.: Algorithms and applications for approximate nonnegative matrix factorization. Comput. Stat. Data Anal. 52(1), 155–173 (2007)
Ertl, B., Luttenberger, S., Paechter, M.: The impact of gender stereotypes on the self-concept of female students in stem subjects with an under-representation of females. Front. Psychol. 8, 703 (2017)
Ho, J.C., et al.: Limestone: high-throughput candidate phenotype generation via tensor factorization. J. Biomed. Inform. 52, 199–211 (2014)
Ho, J.C., Ghosh, J., Sun, J.: Extracting phenotypes from patient claim records using nonnegative tensor factorization. In: Ślezak, D., Tan, A.-H., Peters, J.F., Schwabe, L. (eds.) BIH 2014. LNCS (LNAI), vol. 8609, pp. 142–151. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-09891-3_14
Hosseinmardi, H., Kao, H.T., Lerman, K., Ferrara, E.: Discovering hidden structure in high dimensional human behavioral data via tensor factorization. arXiv preprint arXiv:1905.08846 (2019)
Jiang, S., Simpkins, S.D., Eccles, J.S.: Individuals’ math and science motivation and their subsequent stem choices and achievement in high school and college: a longitudinal study of gender and college generation status differences. Dev. Psychol. 56(11), 2137 (2020)
Kamiran, F., Calders, T.: Data preprocessing techniques for classification without discrimination. Knowl. Inf. Syst. 33(1), 1–33 (2012). https://doi.org/10.1007/s10115-011-0463-8
Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Sansone, D.: Beyond early warning indicators: high school dropout and machine learning. Oxford Bull. Econ. Stat. 81(2), 456–485 (2019)
United States Department of Education. Institute of Education Sciences. National Center for Education Statistics: High School Longitudinal Study, 2009–2013 [United States] (2016). https://doi.org/10.3886/ICPSR36423.v1
Wang, Y., et al.: Rubik: knowledge guided tensor factorization and completion for health data analytics. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1265–1274 (2015)
Acknowledgements
This work was supported by the U.S. Office of Naval Research (ONR N00014-19-1-2625).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Tyler, M., Liu, A., Srinivasan, R. (2021). Behavioral Phenotyping for Predictive Model Equity and Interpretability in STEM Education. In: Roll, I., McNamara, D., Sosnovsky, S., Luckin, R., Dimitrova, V. (eds) Artificial Intelligence in Education. AIED 2021. Lecture Notes in Computer Science(), vol 12749. Springer, Cham. https://doi.org/10.1007/978-3-030-78270-2_64
Download citation
DOI: https://doi.org/10.1007/978-3-030-78270-2_64
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-78269-6
Online ISBN: 978-3-030-78270-2
eBook Packages: Computer ScienceComputer Science (R0)