Designing Affirmative Action Policies under Uncertainty

Autor/inn/en	Hertweck, Corinna; Castillo, Carlos; Mathioudakis, Michael
Titel	Designing Affirmative Action Policies under Uncertainty
Quelle	In: Journal of Learning Analytics, 9 (2022) 2, S.121-137 (17 Seiten)Infoseite zur Zeitschrift PDF als Volltext kostenfreie Datei Verfügbarkeit
Zusatzinformation	ORCID (Hertweck, Corinna) ORCID (Castillo, Carlos) ORCID (Mathioudakis, Michael)
Sprache	englisch
Dokumenttyp	gedruckt; online; Zeitschriftenaufsatz
Schlagwörter	Affirmative Action; Policy Formation; Educational Policy; College Admission; Policy Analysis; Prediction; Artificial Intelligence; Social Justice; Data Use; Foreign Countries; Social Differences; Chile + Suchen Sie Ihr Suchwort? Politische Betätigung; Politics of education; Bildungspolitik; Hochschulzugang; Hochschulzulassung; Zulassung; Politikfeldanalyse; Vorhersage; Künstliche Intelligenz; Soziale Gerechtigkeit; Ausland; Sozialer Unterschied
Abstract	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. (As Provided).
Anmerkungen	Society for Learning Analytics Research. 121 Pointe Marsan, Beaumont, AB T4X 0A2, Canada. Tel: +61-429-920-838; e-mail: info@solaresearch.org; Web site: https://learning-analytics.info/index.php/JLA/index
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2024/1/01