Predictive models assessment based on CRISP-DM methodology for students performance in Colombia - Saber 11 Test

The purpose of this paper is to evaluate several machine learning models under the CRISP-DM methodology in order to determine, through its metrics, the best model for predicting the performance of high school students in the Colombian Caribbean region in the Saber 11º test, while proposing a new met...

Full description

Autores:
Acosta-Solano, Jairo
Lancheros Cuesta, Diana Janeth
Umaña Ibáñez, Samir F.
Coronado-Hernandez, Jairo R.
Tipo de recurso:
Article of journal
Fecha de publicación:
2022
Institución:
Corporación Universidad de la Costa
Repositorio:
REDICUC - Repositorio CUC
Idioma:
eng
OAI Identifier:
oai:repositorio.cuc.edu.co:11323/9221
Acceso en línea:
https://hdl.handle.net/11323/9221
https://doi.org/10.1016/j.procs.2021.12.278
https://repositorio.cuc.edu.co/
Palabra clave:
CRISP-DM methodology
Education
Learning models
National education system
Predictive models
Rights
openAccess
License
© 2021 The Authors. Published by Elsevier B.V
id RCUC2_6da3a98ce7741eacc41ddca04b6cc36e
oai_identifier_str oai:repositorio.cuc.edu.co:11323/9221
network_acronym_str RCUC2
network_name_str REDICUC - Repositorio CUC
repository_id_str
dc.title.eng.fl_str_mv Predictive models assessment based on CRISP-DM methodology for students performance in Colombia - Saber 11 Test
title Predictive models assessment based on CRISP-DM methodology for students performance in Colombia - Saber 11 Test
spellingShingle Predictive models assessment based on CRISP-DM methodology for students performance in Colombia - Saber 11 Test
CRISP-DM methodology
Education
Learning models
National education system
Predictive models
title_short Predictive models assessment based on CRISP-DM methodology for students performance in Colombia - Saber 11 Test
title_full Predictive models assessment based on CRISP-DM methodology for students performance in Colombia - Saber 11 Test
title_fullStr Predictive models assessment based on CRISP-DM methodology for students performance in Colombia - Saber 11 Test
title_full_unstemmed Predictive models assessment based on CRISP-DM methodology for students performance in Colombia - Saber 11 Test
title_sort Predictive models assessment based on CRISP-DM methodology for students performance in Colombia - Saber 11 Test
dc.creator.fl_str_mv Acosta-Solano, Jairo
Lancheros Cuesta, Diana Janeth
Umaña Ibáñez, Samir F.
Coronado-Hernandez, Jairo R.
dc.contributor.author.spa.fl_str_mv Acosta-Solano, Jairo
Lancheros Cuesta, Diana Janeth
Umaña Ibáñez, Samir F.
Coronado-Hernandez, Jairo R.
dc.subject.proposal.eng.fl_str_mv CRISP-DM methodology
Education
Learning models
National education system
Predictive models
topic CRISP-DM methodology
Education
Learning models
National education system
Predictive models
description The purpose of this paper is to evaluate several machine learning models under the CRISP-DM methodology in order to determine, through its metrics, the best model for predicting the performance of high school students in the Colombian Caribbean region in the Saber 11º test, while proposing a new methodology for evaluating the results of the test by regions in order to take into account the socioeconomic particularities of each one of them. The CRISP-DM methodology is taken as a basis due to its maturity, this methodology allows the extraction of business and data knowledge, offers a guide for data preparation, modeling and validation of the models; it is expected that the proposed methodology will be implemented by the Colombian Institute for the Promotion of Higher Education (ICFES), departmental education secretariats and educational institutions. A variety of techniques and tools were used to develop ETL processes to obtain a data set with the most relevant attributes, in order to evaluate four machine learning models developed with the J48 (C4.5), LMT, PART and Multilayer Perceptron algorithms; obtaining that the best data set and the best learning model is obtained using the InfoGain attribute selection method and the LMT decision tree algorithm, respectively. Therefore, this project will facilitate the actors of the National Education System to make decisions for the benefit of students and the quality of education in the country, especially in the Caribbean region.
publishDate 2022
dc.date.accessioned.none.fl_str_mv 2022-06-08T13:28:14Z
dc.date.available.none.fl_str_mv 2022-06-08T13:28:14Z
dc.date.issued.none.fl_str_mv 2022
dc.type.spa.fl_str_mv Artículo de revista
dc.type.coar.fl_str_mv http://purl.org/coar/resource_type/c_2df8fbb1
dc.type.coarversion.fl_str_mv http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.coar.spa.fl_str_mv http://purl.org/coar/resource_type/c_6501
dc.type.content.spa.fl_str_mv Text
dc.type.driver.spa.fl_str_mv info:eu-repo/semantics/article
dc.type.redcol.spa.fl_str_mv http://purl.org/redcol/resource_type/ART
format http://purl.org/coar/resource_type/c_6501
dc.identifier.issn.spa.fl_str_mv 1877-0509
dc.identifier.uri.spa.fl_str_mv https://hdl.handle.net/11323/9221
dc.identifier.url.spa.fl_str_mv https://doi.org/10.1016/j.procs.2021.12.278
dc.identifier.doi.spa.fl_str_mv 10.1016/j.procs.2021.12.278
dc.identifier.instname.spa.fl_str_mv Corporación Universidad de la Costa
dc.identifier.reponame.spa.fl_str_mv REDICUC - Repositorio CUC
dc.identifier.repourl.spa.fl_str_mv https://repositorio.cuc.edu.co/
identifier_str_mv 1877-0509
10.1016/j.procs.2021.12.278
Corporación Universidad de la Costa
REDICUC - Repositorio CUC
url https://hdl.handle.net/11323/9221
https://doi.org/10.1016/j.procs.2021.12.278
https://repositorio.cuc.edu.co/
dc.language.iso.none.fl_str_mv eng
language eng
dc.relation.ispartofjournal.spa.fl_str_mv Procedia Computer Science
dc.relation.references.spa.fl_str_mv [1] Isis Gómez López, Desarrollo sostenible. Elearning, 2020.
[2] ICFES, “ICFES. (2019b). Guía de orientación Saber 11.o 2020-1.” .
[3] R. Ricardo Timarán-Pereira, J. Caicedo-Zambrano, and A. Hidalgo-Troya, “Árboles de decisión para predecir factores asociados al desempeño académico de estudiantes de bachillerato en las pruebas Saber 11°,” Rev. Investig. Desarro. E Innovación, vol. 9, no. 2, 2019.
[4] W. Y. Ayele, “Adapting CRISP-DM for idea mining a data mining process for generating ideas using a textual dataset,” Int. J. Adv. Comput. Sci. Appl., vol. 11, no. 6, pp. 20–32, 2020.
[5] R. Wirth, “CRISP-DM : Towards a Standard Process Model for Data Mining,” Proc. Fourth Int. Conf. Pract. Appl. Knowl. Discov. Data Min., no. 24959, pp. 29–39, 2000.
[6] F. Martinez-Plumed et al., “CRISP-DM Twenty Years Later: From Data Mining Processes to Data Science Trajectories,” IEEE Trans. Knowl. Data Eng., pp. 1–1, 2019.
[7] R. C. Q. Jordi Gironés Roig, Jordi Casas Roma, Julià Minguillón Alfonso, Minería de datos. Editorial UOC, 2017.
[8] ICFES, “Icfes Instituto Colombiano para la Evaluación de la Educación - Portal Icfes.”
[9] S. U. Ibáñez and Jairo R. Coronado-Hernández, “Código desarrollado en R para el proceso ETL.”
[10] C. L. Corso, “Aplicación de algoritmos de clasificación supervisada usando Weka,” Univ. Tecnológica Nac. Fac. Reg. Córdoba, p. 11, 2009.
[11] J. R. (2021): Umaña, Samir; Coronado-Hernández, “Métricas de evaluación de los modelos. figshare. Dataset.”
[12] J. R. Umaña, Samir; Coronado-Hernández, “Estructura del Logistic Model Tree. figshare. Dataset.”
[13] J. R. (2021): Umaña, Samir; Coronado-Hernández, “Código en R y gráfica del árbol generado por el algoritmo rpart. figshare. Dataset.”
dc.relation.citationendpage.spa.fl_str_mv 517
dc.relation.citationstartpage.spa.fl_str_mv 512
dc.relation.citationvolume.spa.fl_str_mv 198
dc.rights.spa.fl_str_mv © 2021 The Authors. Published by Elsevier B.V
Atribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0)
dc.rights.uri.spa.fl_str_mv https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.accessrights.spa.fl_str_mv info:eu-repo/semantics/openAccess
dc.rights.coar.spa.fl_str_mv http://purl.org/coar/access_right/c_abf2
rights_invalid_str_mv © 2021 The Authors. Published by Elsevier B.V
Atribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0)
https://creativecommons.org/licenses/by-nc-nd/4.0/
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.extent.spa.fl_str_mv 6 páginas
dc.format.mimetype.spa.fl_str_mv application/pdf
dc.coverage.country.none.fl_str_mv Colombia
dc.publisher.spa.fl_str_mv Elsevier BV
dc.publisher.place.spa.fl_str_mv Netherlands
institution Corporación Universidad de la Costa
dc.source.url.spa.fl_str_mv https://www.sciencedirect.com/science/article/pii/S1877050921025175
bitstream.url.fl_str_mv https://repositorio.cuc.edu.co/bitstreams/a9454371-e22e-43bb-a060-338f5546e37a/download
https://repositorio.cuc.edu.co/bitstreams/1832ee46-0268-4d8b-8f83-bd0609f2b072/download
https://repositorio.cuc.edu.co/bitstreams/e4f52938-75b9-4701-9900-c39f67d2fa9f/download
https://repositorio.cuc.edu.co/bitstreams/d3d92039-5e7f-42b5-88a4-8b4bfcc01d71/download
bitstream.checksum.fl_str_mv b58d40d1ff88f69d4086e73aafdfc428
e30e9215131d99561d40d6b0abbe9bad
6a379a12c88fd1755e39f143833fa857
850f0e8726eb685eece7b5a602513619
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositorio de la Universidad de la Costa CUC
repository.mail.fl_str_mv repdigital@cuc.edu.co
_version_ 1828166904697585664
spelling Acosta-Solano, JairoLancheros Cuesta, Diana JanethUmaña Ibáñez, Samir F.Coronado-Hernandez, Jairo R.2022-06-08T13:28:14Z2022-06-08T13:28:14Z20221877-0509https://hdl.handle.net/11323/9221https://doi.org/10.1016/j.procs.2021.12.27810.1016/j.procs.2021.12.278Corporación Universidad de la CostaREDICUC - Repositorio CUChttps://repositorio.cuc.edu.co/The purpose of this paper is to evaluate several machine learning models under the CRISP-DM methodology in order to determine, through its metrics, the best model for predicting the performance of high school students in the Colombian Caribbean region in the Saber 11º test, while proposing a new methodology for evaluating the results of the test by regions in order to take into account the socioeconomic particularities of each one of them. The CRISP-DM methodology is taken as a basis due to its maturity, this methodology allows the extraction of business and data knowledge, offers a guide for data preparation, modeling and validation of the models; it is expected that the proposed methodology will be implemented by the Colombian Institute for the Promotion of Higher Education (ICFES), departmental education secretariats and educational institutions. A variety of techniques and tools were used to develop ETL processes to obtain a data set with the most relevant attributes, in order to evaluate four machine learning models developed with the J48 (C4.5), LMT, PART and Multilayer Perceptron algorithms; obtaining that the best data set and the best learning model is obtained using the InfoGain attribute selection method and the LMT decision tree algorithm, respectively. Therefore, this project will facilitate the actors of the National Education System to make decisions for the benefit of students and the quality of education in the country, especially in the Caribbean region.6 páginasapplication/pdfengElsevier BVNetherlands© 2021 The Authors. Published by Elsevier B.VAtribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0)https://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Predictive models assessment based on CRISP-DM methodology for students performance in Colombia - Saber 11 TestArtículo de revistahttp://purl.org/coar/resource_type/c_6501http://purl.org/coar/resource_type/c_2df8fbb1Textinfo:eu-repo/semantics/articlehttp://purl.org/redcol/resource_type/ARThttp://purl.org/coar/version/c_970fb48d4fbd8a85https://www.sciencedirect.com/science/article/pii/S1877050921025175ColombiaProcedia Computer Science[1] Isis Gómez López, Desarrollo sostenible. Elearning, 2020.[2] ICFES, “ICFES. (2019b). Guía de orientación Saber 11.o 2020-1.” .[3] R. Ricardo Timarán-Pereira, J. Caicedo-Zambrano, and A. Hidalgo-Troya, “Árboles de decisión para predecir factores asociados al desempeño académico de estudiantes de bachillerato en las pruebas Saber 11°,” Rev. Investig. Desarro. E Innovación, vol. 9, no. 2, 2019.[4] W. Y. Ayele, “Adapting CRISP-DM for idea mining a data mining process for generating ideas using a textual dataset,” Int. J. Adv. Comput. Sci. Appl., vol. 11, no. 6, pp. 20–32, 2020.[5] R. Wirth, “CRISP-DM : Towards a Standard Process Model for Data Mining,” Proc. Fourth Int. Conf. Pract. Appl. Knowl. Discov. Data Min., no. 24959, pp. 29–39, 2000.[6] F. Martinez-Plumed et al., “CRISP-DM Twenty Years Later: From Data Mining Processes to Data Science Trajectories,” IEEE Trans. Knowl. Data Eng., pp. 1–1, 2019.[7] R. C. Q. Jordi Gironés Roig, Jordi Casas Roma, Julià Minguillón Alfonso, Minería de datos. Editorial UOC, 2017.[8] ICFES, “Icfes Instituto Colombiano para la Evaluación de la Educación - Portal Icfes.”[9] S. U. Ibáñez and Jairo R. Coronado-Hernández, “Código desarrollado en R para el proceso ETL.”[10] C. L. Corso, “Aplicación de algoritmos de clasificación supervisada usando Weka,” Univ. Tecnológica Nac. Fac. Reg. Córdoba, p. 11, 2009.[11] J. R. (2021): Umaña, Samir; Coronado-Hernández, “Métricas de evaluación de los modelos. figshare. Dataset.”[12] J. R. Umaña, Samir; Coronado-Hernández, “Estructura del Logistic Model Tree. figshare. Dataset.”[13] J. R. (2021): Umaña, Samir; Coronado-Hernández, “Código en R y gráfica del árbol generado por el algoritmo rpart. figshare. Dataset.”517512198CRISP-DM methodologyEducationLearning modelsNational education systemPredictive modelsPublicationORIGINALPredictive models assessment based on CRISP-DM methodology.pdfPredictive models assessment based on CRISP-DM methodology.pdfapplication/pdf654350https://repositorio.cuc.edu.co/bitstreams/a9454371-e22e-43bb-a060-338f5546e37a/downloadb58d40d1ff88f69d4086e73aafdfc428MD51LICENSElicense.txtlicense.txttext/plain; charset=utf-83196https://repositorio.cuc.edu.co/bitstreams/1832ee46-0268-4d8b-8f83-bd0609f2b072/downloade30e9215131d99561d40d6b0abbe9badMD52TEXTPredictive models assessment based on CRISP-DM methodology.pdf.txtPredictive models assessment based on CRISP-DM methodology.pdf.txttext/plain37714https://repositorio.cuc.edu.co/bitstreams/e4f52938-75b9-4701-9900-c39f67d2fa9f/download6a379a12c88fd1755e39f143833fa857MD53THUMBNAILPredictive models assessment based on CRISP-DM methodology.pdf.jpgPredictive models assessment based on CRISP-DM methodology.pdf.jpgimage/jpeg13306https://repositorio.cuc.edu.co/bitstreams/d3d92039-5e7f-42b5-88a4-8b4bfcc01d71/download850f0e8726eb685eece7b5a602513619MD5411323/9221oai:repositorio.cuc.edu.co:11323/92212024-09-17 14:24:20.622https://creativecommons.org/licenses/by-nc-nd/4.0/© 2021 The Authors. Published by Elsevier B.Vopen.accesshttps://repositorio.cuc.edu.coRepositorio de la Universidad de la Costa CUCrepdigital@cuc.edu.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