Designing Affirmative Action Policies under Uncertainty




algorithmic fairness, affirmative action, predictive analytics, research paper


We study university admissions under a centralized system that uses grades and standardized test scores to match applicants to university programs. In the context of this system, we explore affirmative action policies that seek to narrow the gap between the admission rates of different socio-demographic groups while still accepting students with high scores. Since there is uncertainty about the score distribution of the students who will apply to each program, it is unclear what policy would have the desired effect on the admission rates of different groups. We address this challenge by using a predictive model trained on historical data to help optimize the parameters of such policies. We find that a learned predictive model does significantly better than relying on the ideal parameters for the last year. At the same time, we also find that a large pool of historical data yields similar results as our predictive approach for our data. Due to the more complex nature of the predictive approach, we conclude that a simpler approach should be preferred if enough data is available (e.g., long-standing, traditional university programs), but not for newer programs and other cases in which our predictive strategy can prove helpful.


Abdulkadiroğlu, A. (2005). College admissions with affirmative action. International Journal of Game Theory, 33(4), 535–549.

Abdulkadiroğlu, A., & Sönmez, T. (2003). School choice: A mechanism design approach. American Economic Review, 93(3), 729–747.

Bacharach, V. R., Baumeister, A. A., & Furr, R. M. (2003). Racial and gender science achievement gaps in secondary education. Journal of Genetic Psychology, 164(1), 115–126.

Balafoutas, L., & Sutter, M. (2012). Affirmative action policies promote women and do not harm efficiency in the laboratory. Science, 335(6068), 579–582.

Bastarrica, M. C., Hitschfeld, N., Marques Samary, M., & Simmonds, J. (2018). Affirmative action for attracting women to STEM in Chile. Proceedings of the Workshop on Gender Equality in Software Engineering (GE 2018), 27 May–3 June 2018, Gothenburg, Sweden (pp. 45–48). ACM.

Bellamy, R. K. E., Dey, K., Hind, M., Hoffman, S. C., Houde, S., Kannan, K., Lohia, P., Martino, J., Mehta, S., Mojsilovic, A., Nagar, S., Ramamurthy, K. N., Richards, J., Saha, D., Sattigeri, P., Singh, M., Varshney, K. R., & Zhang, Y. (2018). AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias.

Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.

Brest, P., & Oshige, M. (1995). Affirmative action for whom? Stanford Law Review, 47(5), 855–900.

Cabalin, C. (2012). Neoliberal education and student movements in Chile: Inequalities and malaise. Policy Futures in Education, 10(2), 219–228.

Crosby, F. J., Iyer, A., & Sincharoen, S. (2006). Understanding affirmative action. Annual Review of Psychology, 57, 585–611.

Davies, R. (2019, November 13). Why is inequality booming in Chile? Blame the Chicago Boys. The Guardian.

DEMRE. (n.d.). Puntaje Ranking [Accessed on 10/28/2019].

Dickson, L. M. (2006). Does ending affirmative action in college admissions lower the percent of minority students applying to college? Economics of Education Review, 25(1), 109–119.

Evans, G. W. (2004). The environment of childhood poverty. American Psychologist, 59(2), 77. 066X.59.2.77

Faucon, L., Olsen, J. K., Haklev, S., & Dillenbourg, P. (2020). Real-time prediction of students’ activity progress and completion rates. Journal of Learning Analytics, 7(2), 18–44.

Friedler, S. A., Scheidegger, C., & Venkatasubramanian, S. (2016). On the (Im)possibility of Fairness. arXiv:1609.07236.

Gale, D., & Shapley, L. S. (1962). College admissions and the stability of marriage. The American Mathematical Monthly, 69(1), 9–15.

Hafalir, I. E., Yenmez, M. B., & Yildirim, M. A. (2013). Effective affirmative action in school choice. Theoretical Economics, 8(2), 325–363.

Hertweck, C. (2020). Designing Affirmative Action Policies under Uncertainty (Master’s thesis). University of Helsinki. Helsinki, Finland.

Hoxby, C. M., & Avery, C. (2012). The Missing “One-Offs”: The Hidden Supply of High-Achieving, Low Income Students (tech. rep.). National Bureau of Economic Research.

Järvelin, K., & Kekäläinen, J. (2002). Cumulated gain-based evaluation of IR techniques. ACM Transactions on Information Systems (TOIS), 20(4), 422–446.

Kawagoe, T., Matsubae, T., & Takizawa, H. (2018). The skipping-down strategy and stability in school choice problems with affirmative action: Theory and experiment. Games and Economic Behavior, 109, 212–239. geb.2017.12.012

Kojima, F. (2012). School choice: Impossibilities for affirmative action. Games and Economic Behavior, 75(2), 685–693.

Lancaster, A., Moses, S., Clark, M., & Masters, M. C. (2020). The positive impact of deliberate writing course design on student learning experience and performance. Journal of Learning Analytics, 7(3), 48–63. 2020.73.5

Long, M. C. (2004). College applications and the effect of affirmative action. Journal of Econometrics, 121(1), 319–342.

Mathioudakis, M., Castillo, C., Barnabo, G., & Celis, S. (2020). Affirmative action policies for top-k candidates selection: With an application to the design of policies for university admissions. Proceedings of the 35th Annual ACM Symposium on Applied Computing (SAC 2020), 30 March–3 April 2020, Brno, Czechia (pp. 440–449). ACM.

McEwan, P. J. (2004). The indigenous test score gap in Bolivia and Chile. Economic Development and Cultural Change, 53(1), 157–190.

Meneses, F., & Cáceres, J. T. (2012). Predicción de notas en Derecho de la Universidad de Chile: ¿sirve el ranking? ISEES: Inclusión Social y Equidad en la Educación Superior, 2012(10), 43–60.

Ministerio de Educación de Chile. (2009). Bases para una pol ́ıtica de formación técnico-profesional en Chile. Informe de la Comisión para el Estudio de la Formación Técnico-Profesional en Chile [Executive Summary]. content/uploads/documento-link-4.pdf

OECD & World Bank. (2009). Reviews of National Policies for Education: Tertiary Education in Chile.

Pelikan, M., Goldberg, D. E., & Cantú-Paz, E. (1999). BOA: The Bayesian optimization algorithm. In W. Banzhaf, J. M. Daida, A. E. Eiben, M. H. Garzon, & V. Honavar (Eds.), Proceedings of the First Annual Conference on Genetic and Evolutionary Computation—Volume 1 (GECCI 1999), 13–17 July 1999, Orlando, FL, USA (pp. 525–532). Morgan Kaufmann Publishers.

Reardon, S. F. (2013). The widening income achievement gap. Educational Leadership, 70(8), 10–16.

Ríos, I., Larroucau, T., Parra, G., & Cominetti, R. (2014). College Admissions Problem with Ties and Flexible Quotas.

Rothstein, R. (2015). The racial achievement gap, segregated schools, and segregated neighborhoods: A constitutional insult. Race and Social Problems, 7(1), 21–30.

Tsoumakas, G., & Katakis, I. (2008). Multi-label classification: An overview. In J. Wang (Ed.), Data Warehousing and Mining: Concepts, Methodologies, Tools, and Applications (pp. 64–74). IGI Global. label-classification/7632

Universidad de Chile. (n.d.). Programa de Ingreso Prioritario de Equidad de Género (PEG) [Accessed 28 October 2019].




How to Cite

Hertweck, C., Castillo, C., & Mathioudakis, M. (2022). Designing Affirmative Action Policies under Uncertainty. Journal of Learning Analytics, 9(2), 121-137.



Research Papers