Proposal of Architecture And Application of Machine Learning (Ml) as A Strategy For The Reduction of University Desertion Levels Due to Academic Factors

Main Article Content

José Ignacio Rodríguez Molano
Leidy Daniela Forero Zea
Yudy Fernanda Piñeros Reina


Introduction:  Machine Learning arises as one of the techniques of artificial intelligence, with the development of computer programs that, through algorithms, access data and use them to learn and predict results. Their application in education allows for the characterization of problems or difficulties in learning through the analysis of student performance.

Objective:  Identification of applications of Machine Learning that can be applied to the educational field accompanied by a proposal of architecture for the application in an environment of personalized education.

Methodology: This article begins with the review of the literature on the characteristics of Machine Learning and academic desertion, with an emphasis on the Colombian case, the Hyper-personalization and its applicability to learning methodologies. Then, a proposal of architecture in a Machine Learning environment is generated in order to mitigate the academic desertion caused by academic factors. Finally, we propose mechanisms for evaluating the proposed architecture, with a subsequent synthesis and discussion of the results.

Conclusions: The construction of a Moodle architecture for the hyper-personalization of learning, is a global perspective of the representative factors proposed for the development of applications through Machine Learning. This could lead to a decrease in levels of university academic desertion because it facilitates the management of knowledge, information and adaptation through the analysis of scenarios.

Originality: The proposed architecture is shown as an application of machine learning in social cases such as academic desertion, allowing the inclusion of automatic learning models with the requirements of an educational environment.

Restrictions: The case for the application for the Hyper-personalization of learning uses an academic approach which can generate invalid results regarding desertion levels.


Download data is not yet available.

Article Details

How to Cite
Rodríguez MolanoJ. I., Forero ZeaL. D., and Piñeros Reina Y. F., “Proposal of Architecture And Application of Machine Learning (Ml) as A Strategy For The Reduction of University Desertion Levels Due to Academic Factors”, ing. Solidar, vol. 15, no. 3, pp. 1-23, Sep. 2019.
Research Articles


[1] E. Himmel, “Modelo de análisis de la deserción estudiantil en la educación superior.,” Calidad en la Educación, vol. 0, no. 17, pp. 91–108, May 2018. DOI:

[2] M. Sánchez, L. Cruz, and R. Ferro, “Modelo de aproximación al comportamiento de la deserción voluntaria universitaria en pregrados de Ingeniería periodo 2015-2018,” Ingeniería solidaria, vol. 14, no. 26, pp. 1–27, 2018. DOI:

[3] L. A. Melo-Becerra, J. E. Ramos-Forero, and P. Oswaldo Hernández-Santamaría, “La educación superior en Colombia: situación actual y análisis de eficiencia,” Desarrollo y Sociedad, pp. 59–111, 2017. DOI: 10.13043/DYS.78.2 Available:

[4] I. G. Maglogiannis, Emerging artificial intelligence applications in computer engineering : real word AI systems with applications in eHealth, HCI, information retrieval and pervasive technologies. IOS Press, 2007.

[5] D. Sisodia and D. S. Sisodia, “Prediction of Diabetes using Classification Algorithms,” Procedia Computer Science, vol. 132, pp. 1578–1585, Jan. 2018. DOI:

[6] S. B. Kotsiantis, I. D. Zaharakis, and · P E Pintelas, “Machine learning: a review of classification and combining techniques,” Artif Intell Rev, vol. 26, pp. 159–190, 2006. DOI:

[7] M. Copeland, J. Soh, A. Puca, M. Manning, and D. Gollob, “Microsoft Azure Machine Learning,” in Microsoft Azure, 2015. Available:

[8] Ministerio de Educación, “Estádisticas de deserción y graduación.,” pp. 1–4, 2016. Available:

[9] Universidad Distrital, “Estadística de la permanencia, graduación y deserción de los estudiantes en la Facultad de Ingeniería en programas de pregrado 2009-2017,” pp. 13–19,47–56, 2018. Available:

[10] S. P. Barragán Moreno and L. González Támara, “Acercamiento a la deserción estudiantil desde la integración social y académica,” Revista de la Educación Superior, vol. 46, no. 183, pp. 63–86, Jul. 2017. DOI:

[11] Ministerio de Educación Nacional, Deserción estudiantil en la educación superior colombiana. pp. 33–134, 2009. Available:

[12] A. Viana, N., Rullán, “Reflections about school dropout in Finland and Puerto Rico,” Education Policy Analysis Archives, vol. 18, pp. 1–33, 2010. DOI:

[13] J. Y. Chung and S. Lee, “Dropout early warning systems for high school students using machine learning,” Children and Youth Services Review, pp. 346–353, 2018. DOI:

[14] M. Tan and P. Shao, “Prediction of student dropout in E-learning program through the use of machine learning method,” International Journal of Emerging Technologies in Learning, vol. 10, no. 1, pp. 11–17, 2015. DOI:

[15] P. Marquès, Las Tecnologías de la Información y las Comunicaciones en el sistema universitario español. Conferencia de Rectores de las Universidades Españolas (CRUE) pp. 41–81, 2008. Available:

[16] A. Lozano and J. Burgos, “El reto de la radio interactiva y la tutoría virtual,” in Tecnología Educativa en un Modelo de Educación a Distancia Centrado en la Persona, 1st ed., México: Limusa, 2015, pp. 241–276. Available:

[17] R. Canales and P. Marquès, “Factores de buenas prácticas educativas con apoyo de las TIC Análisis de su presencia en tres centros educativos,” Educar, pp. 115–133, 2007. Available:

[18] Entrevista R. C. Revista Semana, “Uso de la tecnología en la educación,” Uso de la tecnología en la educación, 2017. Available:

[19] M. I. Jordan and T. M. Mitchell, “Machine learning: Trends, perspectives, and prospects.,” Science (New York, N.Y.), vol. 349, no. 6245, pp. 255–60, Jul. 2015. Available:

[20] INRIA, “Applying machine learning to education,” INRIA (The French National Institute for Computer Science and Applied Mathematics), 2016. Available:

[21] K. S. Hone and G. R. El Said, “Exploring the factors affecting MOOC retention: A survey study,” Computers and Education, pp. 157–168, 2016. DOI:

[22] P. L. Smith and C. L. Dillon, “Comparing distance learning and classroom learning: Conceptual considerations,” American Journal of Distance Education, vol. 13, no. 2, pp. 6–23, Sep. 2009. DOI:

[23] D. Garlan et al., Documenting Software Architectures:Views and Beyond, Second Edi. Pearson, pp. 12–96, 2010. Available:

[24] L. Bass et al., Software Architecture in Practice Third Edition. pp. 78–97, 2013. Available:

[25] Microsoft Azure, “Azure Machine Learning Studio Documentation - Tutorials, API Reference | Microsoft Docs,”, 2017. [Online]. Available:

Most read articles by the same author(s)