Abstract
School dropout is a multidimensional phenomenon with high social and individual economic costs. Predicting its occurrence would enable the ability to promulgate focused and cost-effective public policies. In our research, predictive models were developed using decision trees, administrative data of the individual, and sociodemographic and school-level risk factors. We produced a cost-effective, robust, and stable predictive model to manage risk at the individual and school levels. The model has consequences for public policies because it makes it possible to identify specific schools and individuals that need resources and risk management and allows us to understand which factors most affect dropout over time quantitatively. Thus, long-term policies can be generated that manage these factors so that the prevalence of school abandonment in future cohorts of students is lower than in previous ones.
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
Notes
- 1.
Sistema de Medición de la Calidad de la Educación: https://www.agenciaeducacion.cl/simce/.
- 2.
The results of surveys for parents and students are also linked to the SIMCE measurement process.
- 3.
These data include the Personal and Social Development Indicators (IDPS from its name in Spanish), whose objective is to measure quality in education more broadly, including non-academic aspects, specifically: self-esteem and school motivation, school coexistence environment, participation, and citizen training and hygiene habits and healthy life (Agencia de la Calidad de la Educación 2017).
- 4.
In Chile, a student can enroll in 4 types of schools described according to how they are financed: public, subsidized, private paid, and delegated administration.
- 5.
Value between 0 and 1 is the hit rate of the binary classifier of a given class concerning the total number of cases belonging to that class. The false-negative rate is 1 – recall. This rate is essential because minimizing false negatives ensures that all students who could drop out receive support and are not undetected.
- 6.
Value between 0 and 1 is the hit rate concerning the total predictions that the binary classifier makes for a given class. The false-positive rate is 1 – precision.
- 7.
Recall of the positive class in a binary classifier.
- 8.
Recall of the negative class in a binary classifier.
- 9.
Harmonic mean between the precision and the recall of a class, in this case, the positive one.
- 10.
The importance of a variable is calculated as the mean (standardized between 0 and 1) of the absolute value of its SHAP values.
References
Adelman M, Székely M (2017) An overview of school dropout in Central America: unresolved issues and new challenges for education progress. Eur J Educ Res 6(3, Art no 3). https://doi.org/10.12973/eu-jer.6.3.235
Agencia de la Calidad de la Educación (2021) Indicadores de Desarrollo Personal y Social (IDPS) medidos a través de cuestionarios. Informe Técnico. Accessed: ago. 10, 2021. [Online]. Available: http://bibliotecadigital.mineduc.cl//handle/20.500.12365/4564
Bentéjac C, Csörgő A, Martínez-Muñoz G (2021) A comparative analysis of gradient boosting algorithms. Artif Intell Rev 54(3):1937–1967. https://doi.org/10.1007/s10462-020-09896-5
Bornsheuer JN, Polonyi MA, Andrews M, Fore B, Onwuegbuzie AJ (2011) The relationship between ninth-grade retention and on-time graduation in a Southeast Texas High School 16(2, Art no 2)
Bellei C, Contreras D (2003) Deserción escolar en Chile: contexto y resultados de investigaciones. en 12 años de Escolaridad Oblitatoria, LOM ediciones
Christenson SL, Thurlow ML (2004) School dropouts: prevention considerations, interventions, and challenges. Curr Dir Psychol Sci 13(1 Art no 1). https://doi.org/10.1111/j.0963-7214.2004.01301010.x
Doll JJ, Eslami Z, Walters L (2013) Understanding why students drop out of high school, according to their own reports: are they pushed or pulled, or do they fall out? A comparative analysis of seven nationally representative studies. SAGE Open 3(4, Art no 4). https://doi.org/10.1177/2158244013503834
Dussaillant F (2017) Deserción escolar en Chile. Propuestas para la investigación y la política pública. Doc 18:1–18
Ecker-Lyster M, Niileksela C (2016) Keeping students on track to graduate: a synthesis of school dropout trends, prevention, and intervention initiatives. J-Risk Issues 19(2, Art no 2)
Fortin L, Marcotte D, Diallo T, Potvin P, Royer É (2013) A multidimensional model of school dropout from an 8-year longitudinal study in a general high school population. Eur J Psychol Educ 28(2, Art no 2)
Gasper J, Deluca S, Estacion A (2012) Switching schools: revisiting the relationship between school mobility and high school dropout. Am Educ Res J 49(3, Art no 3) https://doi.org/10.3102/0002831211415250
Gonzalez L, Cramer E (2013) Class placement and academic and behavioral variables as predictors of graduation for students with disabilities. Florida International University
Herbers JE, Reynolds AJ, Chen C (2013) School mobility and developmental outcomes in young adulthood. Dev Psychopathol 25:501–515. https://doi.org/10.1017/S0954579412001204
Jena M, Dehuri S (2020) Decision tree for classification and regression: a state-of-the-art review. Informatica 44(4). https://doi.org/10.31449/inf.v44i4.3023
Kattan RB, Székely M (2017) Analyzing upper secondary education dropout in Latin America through a cohort approach. J Educ Learn 6(4, Art no 4). https://doi.org/10.5539/jel.v6n4p12
Kokkidou E, Rodríguez P, Mondaca J, Matas M (unpublished) El impacto económico de la deserción escolar en Chile
Lundberg SM, Erion GG, Lee S-I (2021) Consistent individualized feature attribution for tree ensembles. ArXiv180203888 Cs Stat, mar. 2019, Accedido: ago. 10, 2021. [Online]. Available http://arxiv.org/abs/1802.03888
Márquez-Vera C, Cano A, Romero C, Noaman AYM, Fardoun HM, Ventura S (2016) Early dropout prediction using data mining: a case study with high school students. Expert Syst 33(1):107–124. https://doi.org/10.1111/exsy.12135
Mduma N, Kalegele K, Machuve D (2019) A survey of machine learning approaches and techniques for student dropout prediction. Data Sci J 18:14. https://doi.org/10.5334/dsj-2019-014
OECD (2010) Overcoming school failure: policies that work. OECD project description
Román M (2013) Factores asociados al abandono y la deserción escolar en américa latina: una mirada en conjunto. REICE Rev Iberoam Sobre Calid Efic Cambio En Educ 11(2, Art no 2)
Rumberger RW (1995) Dropping out of middle school: a multilevel analysis of students and schools. Am Educ Res Assoc 32(3, Art no 3)
Strom RE, Boster FJ (2007) Dropping out of high school: a meta-analysis assessing the effect of messages in the home and in school. Commun Educ October 2014(October 2014). https://doi.org/10.1080/03634520701413804
Stearns E, Glennie E (2006) When and why dropouts leave school: lessons from North Carolina. Youth Soc 38(1, Art no 1)
Şahin Ş, Arseven Z, Kılıç A (2016) Causes of student absenteeism and school dropouts. Int J Instr 6(2, Art no 2). https://doi.org/10.12973/iji.2016.9115a
Sorensen LC (2019) Big Data in educational administration: an application for predicting school dropout risk. Educ Adm Q 55(3):404–446. https://doi.org/10.1177/0013161X18799439
Torres JD, Acevedo D, Gallo LA (2015) Causas y consecuencias de la deserción y repitencia escolar: Una visión general en el contexto latinoamericano. Cult Educ Soc 6(2 Art no 2)
Valenzuela JP, Ruiz C, Contreras M (2021) Revisión de antecedentes sobre exclusión educativa: Una mirada a la deserción y repitencia escolar. Proyecto FONDEF IT17I1006 “Un sistema nacional de protección de trayectorias educativas: disminuyendo la exclusión educativa en la enseñanza escolar y previniendo la deserción en educación superior”, ene. 2019. Accessed: ago. 10, 2021. [Online]. Available http://www.ciae.uchile.cl/download.php?file=noticias/00_1619125708.pdf
Weybright EH, Caldwell LL, Wegner L, Smith EA (2017) Predicting secondary school dropout among South African adolescents: a survival analysis approach. South Afr J Educ 37(2, Art no 2). https://doi.org/10.15700/saje.v37n2a1353
Winding TN, Andersen JH (2015) Socioeconomic differences in school dropout among young adults: the role of social relations. BMC Public Health 1–12. https://doi.org/10.1186/s12889-015-2391-0
Witte K, Cabus S, Thyssen G, Groot W, Brink HM (2013) A critical review of the literature on school dropout. Educ Res Rev 10:13–28. https://doi.org/10.1016/j.edurev.2013.05.002
Witte K, Rogge N (2013) Dropout from secondary education: all’s well that begins well. Eur J Educ II
Zaff JF, Donlan A, Gunning A, Anderson SE, Mcdermott E, Sedaca M (2017) Factors that promote high school graduation: a review of the literature. Educ Psychol Rev 447–476. https://doi.org/10.1007/s10648-016-9363-5
Acknowledgements
We are grateful for the financing granted by the ANID/PIA/Basal Funds for Centers of Excellence FB0003 and ANID-FONDEF IT17I0006 projects.
The authors acknowledge the technical support of Writing Lab, Institute for the Future of Education, Tecnologico de Monterrey, Mexico, in the production of this work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Rodríguez, P., Villanueva, A. (2022). Design, Development, and Evaluation of a Predictive Model for Regular School Dropout in the Chilean Educational System. In: Hosseini, S., Peluffo, D.H., Nganji, J., Arrona-Palacios, A. (eds) Technology-Enabled Innovations in Education. Transactions on Computer Systems and Networks. Springer, Singapore. https://doi.org/10.1007/978-981-19-3383-7_40
Download citation
DOI: https://doi.org/10.1007/978-981-19-3383-7_40
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-3382-0
Online ISBN: 978-981-19-3383-7
eBook Packages: Computer ScienceComputer Science (R0)