Key Predictors of School Dropout in Paraguay: A Big Data Analysis
Article Sidebar
Main Article Content
Abstract
School dropout constitutes a structural challenge in Latin America, carrying profound implications for social and economic development. This study examines the factors associated with educational dropout in the years preceding the completion of middle or secondary education in Paraguay, utilizing administrative data from the Registro Único del Estudiante (RUE), the educational data management system of the Ministry of Education and Science, for the period 2017-2023. A quantitative approach was employed, encompassing descriptive analyses and the application of machine learning models to identify dropout patterns and predict the risk of school abandonment. The study analyzed 706,785 student records, incorporating sociodemographic, academic, and institutional variables. The findings indicate a significant increase in dropout rates between 2019 and 2020, coinciding with the onset of the COVID-19 pandemic, with notable differences observed across gender, educational specialization, and geographic location, where over-age status and grade repetition emerged as critical determinants of dropout. Students enrolled in evening education and vocational training programs exhibited the highest dropout rates. In predictive terms, LASSO regression demonstrated the best performance, achieving an optimal balance between accuracy and sensitivity in identifying at-risk students. These results highlight the importance of leveraging extensive data analysis and advanced modeling techniques to strengthen school retention policies and develop evidence-based early intervention strategies. However, challenges remain concerning the quality and comprehensiveness of educational data, the need to explore emerging artificial intelligence methodologies, and the integration of psychosocial and economic factors to achieve a holistic understanding of school dropout and its determinants.
Key words: Dropouts, Secondary Education, Socioeconomic Background, Data Science, Predictor Variables.
Article Details
References
Abideen, Z. u., Mazhar, T., Razzaq, A., Haq, I., Ullah, I., Alasmary, H., & Mohamed, H. G. (2023). Analysis of Enrollment Criteria in Secondary Schools Using Machine Learning and Data Mining Approach. Electronics, 12(3), 694. https://doi.org/10.3390/electronics12030694
Ajjawi, R., Dracup, M., Zacharias, N., Bennett, S., y Boud, D. (2020). Persisting students’ explanations of and emotional responses to academic failure. Higher Education Research & Development, 39(2), 185-199. https://doi.org/10.1080/07294360.2019.1664999
Alyahyan, E., y Düştegör, D. (2020). Predicting academic success in higher education: literature review and best practices. International Journal of Educational Technology in Higher Education, 17(1), 3. https://doi.org/10.1186/s41239-020-0177-7
Alladatin, J., Lionel, R., y Insaf, A.- chikh. (2023). School principal’s training programs, challenges, and improvement opportunities: rapid review. International Journal of Educational Innovation and Research, 3(1), 17–26. https://doi.org/10.31949/ijeir.v3i1.6830
Amaya-Amaya, A., Huerta-Castro, F., y Flores-Rodríguez, C. O. (2020). Big Data, una estrategia para evitar la deserción escolar en las IES. Revista Iberoamericana de Educación Superior, 11(31), 166-178. https://doi.org/10.22201/iisue.20072872e.2020.31.712
Arias Ortiz, E., Eusebio, J., Pérez Alfaro, M., Vásquez, M., y Zoido, P. (2021). Los Sistemas de Información y Gestión Educativa (SIGED) de América Latina y el Caribe: la ruta hacia la transformación digital de la gestión educativa. https://doi.org/10.18235/0003345
Flores Satalaya, J. M. (2025). El machine learning para abordar el abandono escolar: Una revisión de los modelos más innovadores. Ciencia Latina Revista Científica Multidisciplinar, 8(6), 10993-11027. https://doi.org/10.37811/cl_rcm.v8i6.15824
Gutiérrez-de-Rozas, B., López-Martín, E., y Carpintero, E. (2023). Análisis del abandono educativo temprano en España: condicionantes del abandono y motivos para regresar al sistema educativo. Revista de Investigación Educativa, 41(2), 523-549. https://doi.org/10.6018/rie.546521
Insfrán-Coronel, Enrique-Sánchez, Beck, López-Fernández, García Torres (2024). Analysis of School Dropout Rate in Paraguay Using a Machine Learning Approach, en H. Quinti´an et al. (Eds.): ICEUTE 2024/CISIS 2024, LNNS 957, 312–321, 2024. https://doi.org/10.1007/978-3-031-75016-8_29
Kocsis, Á., & Molnár, G. (2024). Factors influencing academic performance and dropout rates in higher education, 1-19. https://doi.org/10.1080/03054985.2024.2316616
Krüger, J. G., Britto Jr., A. de S., & Barddal, J. P. (2023). An explainable machine learning approach for student dropout prediction. Expert Systems with Applications, 233, december, 120933. https://doi.org/10.1016/j.eswa.2023.120933
Montero-Sieburth, M., y Turcatti, D. (2022) Preventing disengagement leading to early school leaving: pro-active practices for schools, teachers and families, Intercultural Education, 33(2), 139-155. https://doi.org/10.1080 /14675986.2021.2018404
Nait Belaid, Y. (2021). A critical analysis of policies to fight illiteracy and school dropout in rural Morocco. International Journal of Advanced Research , 9 (Aug), 254-269.
https://dx.doi.org/10.21474/IJAR01/13259
Ortiz-Lozano, J. M., Aparicio-Chueca, P., Triadó-Ivern, X. M., & Arroyo-Barrigüete, J. L. (2023). Early dropout predictors in social sciences and management degree students. Studies in Higher Education, 49(8), 1303–1316. https://doi.org/10.1080/03075079.2023.2264343
Ramsdal, G.H.; Wynn, R. Theoretical Basis for a Group Intervention Aimed at Preventing High School Dropout: The Case of ‘Guttas Campus’. Int. J. Environ. Res. Public Health 2022, 19, 17025. https://doi.org/10.3390/ijerph192417025
Rodríguez, P., Delgado Villanueva, A., Dombrovskaia, L., & Valenzuela, J. P. (2023). A methodology to design, develop, and evaluate machine learning models for predicting dropout in school systems: the case of Chile. Education and Information Technologies, 28, 10103–10149. https://doi.org/10.1007/s10639-022-11515-5
Segura, M., Mello, J., & Hernández, A. (2022). Machine learning prediction of university student dropout: Does preference play a key role?. Mathematics, 10(18), 3359. https://doi.org/10.3390/math10183359
Serrano, K., Sierra, Y., Rios-Cruz, S., Pardo, F. 2024 Machine Learning models for predicting academic withdrawal in college students. Conference: 2024 Congreso Internacional de Innovación y Tendencias en Ingeniería (CONIITI) 10.1109/CONIITI64189.2024.10854829
Smith Uldall, J., & Gutiérrez Rojas, C. (2022). An Application of Machine Learning in Public Policy: Early Warning Prediction of School Dropout in the Chilean Public Education System. Multidisciplinary Business Review, 15(1), 20–35. https://doi.org/10.35692/07183992.15.1.4
Venkatesan R.G. &, Mappillairaju, B. (2023). Detection of hotspots of school dropouts in India: A spatial clustering approach. PLoS ONE 18(1): e0280034. https://doi.org/10.1371/journal.pone.0280034
Zapata-Medina, D.; Espinosa-Bedoya, A.; Jiménez-Builes, J.A. Improving the Automatic Detection of Dropout Risk in Middle and High School Students: A Comparative Study of Feature Selection Techniques. Mathematics 2024, 12, 1776. https://doi.org/10.3390/math12121776
Zengin, M. (2021). Investigation of High School students’ dropout risk level. International Journal of Education, 9(S1), 59-68. https://doi.org/10.34293/education.v9iS1-May.4000
European Education Area (2022). Early School Leaving Policies in the EU. European Commission. Recuperado de https://education.ec.europa.eu/pt-pt/education-levels/school-education/early-school-leaving
Instituto Desarrollo (2013). Factores de la deserción escolar en Paraguay. Recuperado de https://desarrollo.org.py/admin/app/webroot/pdf/publications/08-10-2015-16-45-20-848785920.pdf
Instituto Nacional de Estadística (INE, 2024). Encuesta Permanente de Hogares Continua 2023: Datos sobre asistencia escolar en Paraguay. Recuperado de https://www.ine.gov.py/noticias/1890/el-ine-comparte-datos-sobre-la-educacion-paraguaya
UNESCO (2010). Desafíos educativos y estrategias de retención escolar en América Latina y el Caribe. Recuperado de https://unesdoc.unesco.org/ark:/48223/pf0000190771
El País (2025). El círculo virtuoso de la Formación Profesional en Europa. Diario El País. Recuperado de https://elpais.com/opinion/2025-01-30/el-circulo-virtuoso-de-la-fp.html
Comisión Económica para América Latina y el Caribe (CEPAL). (2024). Prevención y reducción del abandono escolar en América Latina y el Caribe. CEPAL. https://repositorio.cepal.org/server/api/core/bitstreams/b80b4d28-e4df-4c5c-9659-dd78d4d1b527/content