Analisitica Académica en La Educación
Analisitica Académica en La Educación
Analisitica Académica en La Educación
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 3 8 ·
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 3 9 ·
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 4 0 ·
La analítica de datos educativos se puede Al hablar de analítica hay que tener claridad
sintetizar según (Clow, 2013) y (Siemens, 2013) que este término involucra diversas técnicas,
en los siguientes pasos: herramientas y métodos que por lo general se
traslapan, tales como como son la estadística
• Pregunta de investigación: Consiste en (Baepler & Murdoch, 2010b), inteligencia de
definir el problema y en tener claridad de negocios (Argonza, 2016), minería de datos
que es lo que se pretende resolver, a quien (García-González et al., 2019) y aprendizaje
o quienes beneficiará dicha solución. automático (Burman & Som, 2019). Métodos
que tiene por tarea desafiante el recopilar,
• Recolección de datos: los datos pueden
limpiar, transformar y analizar múltiples datos
proceder de diferentes fuentes (sistema
provenientes de diversas fuentes contribuyendo
académico, de bibliotecas, de gestión de
al futuro, con especial referencia al contexto
aprendizaje) y en múltiples formatos (hojas
de la educación desarrollando modelos
de cálculo, registros en papel, bases de
predictivos para abordar problemas críticos
datos).
en la educación superior (Figura 2). El uso
• Reportar información: plantea el desarrollo de Analítica en educación posee dos grandes
de informes y análisis de la información con enfoques: la Analítica del Aprendizaje que se
el fin de identificar tendencias, patrones y orienta al proceso de enseñanza y aprendizaje
correlaciones éntrelas variables analizadas. y sus diferentes actores (Ferguson, 2012) ; y
la Analítica Académica que se centra en los
• Análisis y Predicción: es una etapa indicadores que permiten optimizar la labor
importante de la analítica que involucra el social de la educación permitiendo comparar
desarrollo de modelos usando herramientas resultados entre instituciones (Daniel, 2015b).
estadísticas, de minería de datos o de Involucra análisis en diferentes niveles de la
aprendizaje automático. institución superior tales como: departamentos,
proyectos curriculares, facultades y hasta
• Acción/ realimentación: conlleva a la
universidades
toma de decisiones por parte de docentes,
estudiantes e instituciones basadas en la
evidencia (datos).
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 4 1 ·
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 4 2 ·
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 4 3 ·
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 4 4 ·
Regresión
Regresión logística
(Wheeler et al., 2018) 323 logística No especifica
multivariada
multivariada
(Liu et al., 2018) Series de tiempo 325 Series de tiempo No especifica
Algoritmo de bosque Algoritmo De
(Limsathitwong et al., 2018) 2880 RapidMiner
aleatorio bosque aleatorio
(Lima et al., 2018) k-Means y C5.0 1844 k-Means y C5.0 Excel - R free
(Hirokawa, S. 2018) SVM 480 SVM WEKA
Árbol de decisión C4.5,
(Wati et al., 2018) 279 Naive Bayes RAPIDMINER
Naive Bayes
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 4 5 ·
Algoritmo de
Algoritmo de clasificación
(Vora & Rajamani, 2019) 456 clasificación Java
hibrido
hibrido
Naïve Bayes, árbol J48, Árbol de decisión
(Salal et al., 2019 ) 21 WEKA
Bosque aleatorio J48
(Amazona & Hernandez, Naive Bayes, árbol de Redes Deep
300 RAPIDMINER
2019) decisión, Deep Learning Learning
Árbol de decisión ID3,
(Qowidho et al., 2019) 230 C4,5 RAPIDMINER
C4.5
(S. S. M. Ajibade et al.,
Arbol de decision, KNN,
2019)Educational Data 500 Árbol de decisión -
SVM, Bagging, Bosting
Mining (EDM
KNN, Naive Bayes, árbol
(Mohammadi et al., 2019) 230 KNN WEKA
de decisión
KNN, árbol decisión,
(Wiyono& Tegal,2019) 382 SVM WEKA
SVM
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 4 6 ·
Regresión logística y
480 SVM 78% WEKA
SVM
Arbol de decison,KNN,
(L. Contreras et al., 2020) 1620 Percepetrón PYTHON
SVM,perceptrón
(Viloria et al., 2020) ADTree, J48
AD tree
RandomTree, REPTree 1200 WEKA
98.6%
SimpleCart
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 4 7 ·
redes neuronales
(Urteaga et al., 2020) KNN, redes neuronales - R
97%
(Castrillón et al., 2020) J48 460 91,67% WEKA
Redes neUronales,SVM, Redes
(Mengash, 2020b) arbol de decisión, Naive 2.039 neuronales WEKA
Bayes 79.22%
K vecino más cercano, Árbol de
(L. E. Contreras et al., 2020) SVC, perceptrón y árbol 2114 decisión PYTHON
de decisión 85,80%
arbol de
(Hasan et al., 2020)
decision, bosque
aleatorio,Boosting, 4413 AdaBoost PYTHON
AdaBoost, Gradient
(Hasan et al., 2020 Boosting (XGBoost)
Bosque aleatorio, árbol
de decisión, Naive Bosque
(Hassan et al., 2020) 772 PYTHON
Bayes, Regresión aleatorio
Logística, KNN,SVM
(Zacharias & Athanasios, Red
Red neuronal 76 WEKA
neuronal
2020)
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 4 8 ·
Tabla 3 Clasificación de trabajos según enfoque y campos de aplicación para la Analítica Académica
(M. K. Khalil et al., 2018); (Wheeler et al., 2018);(David & Anastasija, 2019); (Vora
Graduación
& Rajamani, 2019); (Kauffman et al., 2019)
(Hernández et al., 2016); (Hasbun et al., 2016); (Devasia et al., 2016); (Merchán-
rubiano et al., 2017); (Liu et al., 2018); (Limsathitwong et al., 2018); (Lima et al.,
Deserción
2018); (Lasarte et al., 2020); (Tenpipat & Akkarajitsakul, 2020); (Medina et al.,
2020), (L. Contreras et al., 2020)
(Echegaray-calderon & Barrios-aranibar, 2015); (Pradeep et al., 2015); (Dixson
et al., 2016); (Ahamed et al., 2016); (Razaque et al., 2017); (Stanko et al., 2017);
(QIN et al., 2017); (Costa et al., 2017); (Hirokawa, S. 2018); (Wati et al., 2018);
(Miguéis et al., 2018); (Burgos et al., 2018); (Kaunang & Rotikan, 2018); (S. M.
Rendimiento Ajibade et al., 2019); (Nabizadeh et al., 2019); (Martín, 2019); (Kwankajonwong
académico et al., 2019); (Herodotou et al., 2019); (Francis & Babu, 2019); (Vora & Ra-
jamani, 2019); (Salal et al., 2019 ); (Amazona & Hernandez, 2019); (Qowidho
et al., 2019); (S. S. M. Ajibade et al., 2019); (Mohammadi et al., 2019); (Wiyono,
Abidin, Bersama, Lor, & Tegal, 2019); (Adekitan & Noma-Osaghae, 2019); (Ni-
eto et al., 2019); (Francis & Babu, 2019); (Hussain, Zhu, Zhang, Abidi, & Ali,
2019); (Tan et al., 2020); (Mavani, et al., 2020); (Mengash, 2020a); (Tomasevic
et al., 2020); (Bhutto et al., 2020); (Viloria et al., 2020); (Urteaga et al., 2020);
(Castrillón et al., 2020); (Mengash, 2020b); (L. E. Contreras et al., 2020); (Hasan
et al., 2020); (Hassan et al., 2020); (Zacharias & Athanasios, 2020)
SOCIALIZACIÓN DE LA ANALÍTICA EN
10
EDUCACIÓN SUPERIOR Revista Congreso
Con el fin de identificar si los trabajos 8
relacionados con analítica académica han sido
6
publicados por medio de revistas revisadas por
pares o por medio de conferencias, se muestra 4
en la Figura 4 un comparativo de trabajo
2
publicados durante el periodo de investigación
en revistas de alto impacto y conferencias para 0
cada uno de los campos de la analítica aplicada 2015 2016 2017 2018 2019 2020
15
internacionales. Esto en nuestro criterio es debido
Cantidad de
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 4 9 ·
10
Revista Congreso
8
4
20
2
investigaciones
15
Cantidad de
0
10 2015 2016 2017 2018 2019 2020
Año
5
0
20
2015 2016 2017 2018 2019 2020
Año
investigaciones
15
Cantidad de
10
Figura 5. Número de documentos según la investigación referencial para la analítica académica en
5 educación superior
0
Realizando un análisis
2015
sobre
2016
cuáles
2017
son2018
los 2019
en investigaciones
2020
aplicadas a la educación
métodos o algoritmos que se han estado utilizando
20 Año
cuando de predicción de fenómenos se trata. El
para estudiar y/o predecir algunos aspectos enfoque hacia el campo de la minería de datos
Arboles de decisión
dentro del campo de la analítica académica, se y el aprendizaje
Redes automático
Neuronales se evidencia con
elaboró la Figura 6 donde se aprecia que las SVM
el uso de algoritmos como redes neuronales,
Cantidad de Métodos
13 1 1 1 1 1 1 1
Algoritmo De bosque aleatorio
0 KNN
10 Correlación estadística
cantidad
10 Regresion
Método usadologistica
según investigación referencial
Naive Bayesian
7 Regresión lineal
5 Algoritmo hibrido
4 4
3
2 2 2
1 1 1 1 1 1 1
0
cantidad
Método usado según investigación referencial
Figura 6. Algoritmos o métodos usados en trabajos relacionados con analítica Académica a partir de la
revisión bibliográfica
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 5 0 ·
Figura 7. Países que han realizado más publicaciones de analítica académica según la revisión
bibliográfica.
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 5 1 ·
graduados por cohorte y los mejores campos de Amazona, M. V., & Hernandez, A. A. (2019).
acción de un grupo de estudiantes al terminar la Modelling Student Performance Using Data
carrera universitaria, así como a los indicadores Mining Techniques. Proceedings of the 2019
anteriormente mencionados. Pero tal como lo 5th International Conference on Computing
menciona (Daniel, 2015a), la tecnología para and Data Engineering - ICCDE’ 19, 36–40.
entregar este potencial es aún muy joven y la https://doi.org/10.1145/3330530.3330544
investigación en la comprensión de la utilidad
Argonza, J. (2016). Big data en la educación.
pedagógica está todavía en su infancia.
Revista Digital Universitaria, 17(1), 1–16.
REFERENCIAS BIBLIOGRÁFICAS http://www.revista.unam.mx/vol.17/num1/
art06/
Adekitan, A. I., & Noma-Osaghae, E. (2019).
Data mining approach to predicting Avella, J. T., Kebritchi, M., Nunn, S. G., &
the performance of first year student Kanai, T. (2016). Learning analytics
in a university using the admission methods, benefits, and challenges in
requirements. Education and Information higher education: A systematic literature
Technologies, 24(2), 1527–1543. https:// review. Journal of Asynchronous Learning
doi.org/10.1007/s10639-018-9839-7 Network, 20(2). https://doi.org/10.24059/
olj.v20i2.790
Ahamed, A. T. M. S., Mahmood, N. T., & Rahman,
R. M. (2016). Prediction of HSC Examination Baepler, P., & Murdoch, C. (2010a). Academic
Performance using Socioeconomic , Analytics and Data Mining in Higher
Psychological and Academic Factors. Education. International Journal for the
International Conference on Electrical and Scholarship of Teaching and Learning, 4(2).
Computer Engineering, 263–266. https://doi.org/10.20429/ijsotl.2010.040217
Ajibade, S. M., Ahmad, N. B., & Shamsuddin, Baepler, P., & Murdoch, C. J. (2010b).
S. M. (2019). An Heuristic Feature International Journal for the Scholarship of
Selection Algorithm to Evaluate Academic Teaching and Learning Academic Analytics
Performance of Students. 10th Control and and Data Mining in Higher Education
System Graduate Research Colloquium Academic Analytics and Data Mining in
(ICSGRC, 2–3. Higher Education. International Journal
for the Scholarship of Teaching and
Ajibade, S. S. M., Bahiah Binti Ahmad, N., Learning, 4(2). https://doi.org/10.20429/
& Mariyam Shamsuddin, S. (2019). ijsotl.2010.040217
Educational Data Mining: Enhancement
of Student Performance model using Bhutto, S., Siddiqui, I. F., Arain, Q. A., & Anwar,
Ensemble Methods. IOP Conference M. (2020). Predicting Students’ Academic
Series: Materials Science and Engineering, Performance Through Supervised Machine
551(1). https://doi.org/10.1088/1757- Learning. ICISCT 2020 - 2nd International
899X/551/1/012061 Conference on Information Science and
Communication Technology. https://doi.
org/10.1109/ICISCT49550.2020.9080033
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 5 2 ·
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 5 3 ·
Educational Data Mining. International Francis, B. K., & Babu, S. S. (2019). Predicting
Conference on Data Mining and Advanced Academic Performance of Students Using
Computing (SAPIENCE), 91–95. a Hybrid Data Mining Approach. Journal
of Medical Systems, 43(6). https://doi.
Dixson, D. D., Worrell, F. C., Olszewski- org/10.1007/s10916-019-1295-4
Kubilius, P., & Subotnik, R. F. (2016).
Beyond perceived ability: the contribution García-González, J. R., Sánchez-Sánchez,
of psychosocial factors to academic P. A., Orozco, M., & Obredor, S. (2019).
performance. Annals of the New York Extracción de Conocimiento para la
Academy of Sciences, 1377(1), 67–77. Predicción y Análisis de los Resultados
https://doi.org/10.1111/nyas.13210 de la Prueba de Calidad de la Educación
Superior en Colombia Knowledge Capture
Dyckhoff, A. L., Zielke, D., Bültmann, M., for the Prediction and Analysis of Results
Chatti, M. A., & Schroeder, U. (2012). of the Quality Test of Higher Education in
Design and implementation of a learning Colombia. Revista Formación Universitaria,
analytics toolkit for teachers. Educational 12(4), 55–62. https://doi.org/10.4067/
Technology and Society, 15(3), 58–76. S0718-50062019000400055
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 5 4 ·
Hasan, R., Palaniappan, S., Mahmood, S., Iten, L., Arnold, K., & Pistilli, M. (2008). Mining
Abbas, A., Sarker, K. U., & Sattar, M. U. Real-Time Data to Improve Student
(2020). Predicting student performance Success in a Gateway Course. Eleventh
in higher educational institutions using Annual TLT Conference.
video learning analytics and data mining
Janani, P., Verma, S., Natarajan, S., & Sinha,
techniques. Applied Sciences , 10(11).
A. K. (2019). Communication Using
https://doi.org/10.3390/app10113894
IoT. In Information and Communication
Hasbun, T., Araya, A., & Villalon, J. (2016). Technology for Sustainable Development,
Extracurricular activities as dropout Advances in Intelligent Systems and
prediction factors in higher education Computing. Springer Singapore. https://
using decision trees. 16th International doi.org/10.1007/978-981-13-7166-0
Conference on Advanced Learning
Kauffman, C., Derazin, M., Asmar, A., &
Technologies Extracurricular, 3–5. https://
Kibble, J. (2019). Patterns of medical
doi.org/10.1109/ICALT.2016.66
student engagement in a second-year
Hassan, H., Ahmad, N. B., & Anuar, S. (2020). pathophysiology course: relationship to
Improved students’ performance prediction USMLE Step 1 performance. Advances in
for multi-class imbalanced problems Physiology Education, 43(01), 512–518.
using hybrid and ensemble approach in https://doi.org/10.1152/advan.00082.2019
educational data mining. Journal of Physics,
Kaunang, F. J., & Rotikan, R. (2018). Students’
1529(5). https://doi.org/10.1088/1742-
academic performance prediction using
6596/1529/5/052041
data mining. Proceedings of the 3rd
Hernández, A. G., Meléndez, R. A., Morales, L. International Conference on Informatics
A., García, A., Tecpanecatl, J. L., & Algredo, and Computing, ICIC 2018, 1–5. https://
I. (2016). Comparative Study of Algorithms doi.org/10.1109/IAC.2018.8780547
to Predict the Desertion in the Students
Khalil, M. K., Hawkins, H. G., Crespo, L. M.,
at the ITSM-Mexico. LATIN AMERICA
& Buggy, J. (2018). The Design and
TRANSACTIONS, 14(11), 4573–4578.
Development of Prediction Models
Herodotou, C., Rienties, B., Boroowa, A., for Maximizing Students ’ Academic
& Zdrahal, Z. (2019). A large ‑ scale Achievement. Medical Science Educator,
implementation of predictive learning 111–117.
analytics in higher education : the teachers
Khalil, M., Khalil, M., & Ebner, M. (2015).
’ role and perspective. In Educational
Learning Analytics: Principles and
Technology Research and Development
Constraints. EdMedia: World Conference
(Vol. 67, Issue 5). Springer US. https://doi.
on Educational Media and Technology,
org/10.1007/s11423-019-09685-0
2015(1), 1789–1799. https://www.
Hirokawa, S. (2018). Key attribute for predicting learntechlib.org/p/151455/
student academic performance. ACM
Kwankajonwong, N., Ongprakobkul, C., Qureshi,
International Conference Proceeding
S. P., Watanatada, P., Thanprasertsuk, S.,
Series, 308–313. https://doi.
& Bongsebandhu-phubhakdi, S. (2019).
org/10.1145/3290511.3290576
Attitude, but Not Self-Evaluated Knowledge,
Correlates with Academic Performance
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 5 5 ·
Lasarte, O. F., Díaz, E. R., Palacios, E. G., Martín, A. N. (2019). Variables motivacionales y
& Fernández, A. R. (2020). The role cognitivas predictivas del rendimiento en
of social support in school adjustment estudiantes universitarios de ciencias de la
during Secondary Education. 32(1), salud Cognitive and motivational predictive
100–107. https://doi.org/10.7334/ variables associated with performance in
psicothema2019.125 University Students of Health Sciences.
33(1), 1–30.
Lauría, E., Moody, E., Jayaprakash, S.,
Jonnalagadda, N., & Baron, J. (2013). Medina, E. C., Chunga, C. B., Armas-aguirre,
Open academic analytics initiative: initial J., Grandón, E. E., & Bío-bío, U. (2020).
research findings. Proceedings of the Third Modelo predictivo para reducir el índice de
International Conference on Learning deserción de estudiantes universitarios en
Analytics and Knowledge, 150–154. el Perú : Redes Bayesianas vs . Árboles
de Decisión Predictive model to reduce the
Lima, J., Alves, P., Pereira, M., & Almeida, S. dropout rate of Decision Trees. 15th Iberian
(2018). Using Academic Analytics to Predict Conference on Information Systems and
Dropout Risk in Engineering Courses. Technologies (CISTI), June, 24–27.
European Conference on E-Learning.
Mengash, H. A. (2020a). Using data mining
Limsathitwong, K., Tiwatthanont, K., & techniques to predict student performance
Yatsungnoen, T. (2018). Dropout Prediction to support decision making in university
System to Reduce Discontinue Study admission systems. IEEE Access, 8,
Rate of Information Technology Students. 55462–55470. https://doi.org/10.1109/
International Conference on Business and ACCESS.2020.2981905
Industrial Research (ICBIR), 110–114.
Mengash, H. A. (2020b). Using data mining
Liu, H., Wang, Z., Benachour, P., & Tubman, P. techniques to predict student performance
(2018). A Time Series Classification Method to support decision making in university
for Behaviour-Based Dropout Prediction. admission systems. IEEE Access, 8,
18th International Conference on Advanced 55462–55470. https://doi.org/10.1109/
Learning Technologies A, 191–195. https:// ACCESS.2020.2981905
doi.org/10.1109/ICALT.2018.00052
Merchán-rubiano, S., Beltrán-gómez, A., &
Long, P., Siemens, G., Conole, G., & Gašević, Duarte-garcía, J. (2017). Engineering
D. (2011). LAK ’11. Proceedings of the Students´ Academic Performance
1st International Conference on Learning Prediction using ICFES Test Scores and
Analytics and Knowledge, 195. https:// Demo- graphic Data. Ingeniería Solidaria,
iucat.iu.edu/iub/13609333 13(21).
Mahroeian, H., Daniel, B., & Butson, R. (2017). Miguéis, V. L., Freitas, A., Garcia, P. J. V., & Silva,
The perceptions of the meaning and A. (2018). Early segmentation of students
value of analytics in New Zealand higher according to their academic performance:
education institutions. International A predictive modelling approach. Decision
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 5 6 ·
Support Systems, 115, 36–51. https://doi. Higher Education, 1(2), 727–742. http://
org/10.1016/j.dss.2018.09.001 er.educause.edu/~/media/files/article-
downloads/erm0742.pdf
Mohammadi, M., Dawodi, M., Tomohisa, W., &
Ahmadi, N. (2019). Comparative study of Pradeep, A., Das, S., & Kizhekkethottam, J. J.
supervised learning algorithms for student (2015). Students Dropout Factor Prediction
performance prediction. 1st International Using EDM Techniques. International
Conference on Artificial Intelligence in Conference on Soft-Computing and
Information and Communication, ICAIIC Network Security.
2019, 124–127. https://doi.org/10.1109/
QIN, F., ZHU, L., CHENG, Z., & ZHANG, Q.
ICAIIC.2019.8669085
(2017). Research on Student Performance
Murnion, P., & Helfert, M. (2013). Academic Evaluation Based on Random Forest.
Analytics in quality assurance using DEStech Transactions on Engineering
organisational analytical capabilities and Technology Research, eeta, 387–
A User-level Usage Analytics in Cloud 393. https://doi.org/10.12783/dtetr/
Based Applications View project Insight eeta2017/7762
View project. In U. Oxford (Ed.), Annual
Qowidho, T., Zarlis, M., Nababan, E. B., Agusnady,
Conference of the UK Academy of
A., & Sembiring, B. S. (2019). Analysis
Information Systems (UKAIS). https://doi.
of c4.5 and ID3 Methods in Determining
org/10.13140/2.1.3368.1600
Student Graduation. Journal of Physics:
Nabizadeh, S., Hajian, S., Sheikhan, Z., & Conference Series, 1255(1). https://doi.
Rafiei, F. (2019). Prediction of academic org/10.1088/1742-6596/1255/1/012025
achievement based on learning strategies
Razaque, F., Soomro, N., Ahmed, S., Soomro,
and outcome expectations among medical
S., Samo, J. A., & Dharejo, H. (2017).
students. BMC Medical Education, 19(1),
Using Naïve Bayes Algorithm to Students
1–11. https://doi.org/10.1186/s12909-019-
’ bachelor Academic Performances
1527-9
Analysis. Conferencia Internacional IEEE
Nieto, Y., Garcia, V., Montenegro, C., Gonzalez, Sobre Tecnologías de Ingeniería y Ciencias
C., & Gonzalez, R. (2019). Usage of Aplicadas (ICETAS), 1–5.
Machine Learning for Strategic Decision
Salal, Y. K., Abdullaev, S. M., & Kumar, M.
Making at Higher Educational Institutions.
(2019). Educational data mining: Student
IEEE Access, 7, 75007–75017. https://doi.
performance prediction in academic.
org/10.1109/ACCESS.2019.2919343
International Journal of Engineering and
Norris, D. M., & Lefrere, P. (2011). Transformation Advanced Technology, 8(4C), 54–59.
through expeditionary change using
Salcedo, A. (2010). Desertion in Colombian
online learning and competence-building
Universities. Revista Academia y
technologies. Research in Learning
Virtualidad, 3(1), 50–60. http://www.
Technology, 19(1), 1741–1629. https://doi.
alfaguia.org/alfaguia/files/1319043663_03.
org/10.3402/rlt.v19i1.17105
pdf
Oblinger, G., Campbell, J. P., Deblois, P. B., &
Oblinger, D. G. (2007). Academic Analytics:
A New Tool for a New Era. Research in
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 5 7 ·
Schroeder, U. (2009). Web-Based Learning – Urteaga, I., Siri, L., & Garófalo, G. (2020).
Yes We Can! (pp. 25–33). Springer, Berlin, Predicción temprana de deserción
Heidelberg. https://doi.org/10.1007/978-3- mediante aprendizaje automático en
642-03426-8_3 cursos profesionales en línea. RIED.
Revista Iberoamericana de Educación
Siemens, G. (2013). Learning Analytics. a Distancia, 23(2), 147. https://doi.
American Behavioral Scientist, org/10.5944/ried.23.2.26356
57(10), 1380–1400. https://doi.
org/10.1177/0002764213498851 Viberg, O., Hatakka, M., Bälter, O., & Mavroudi,
A. (2018). The current landscape of
Stanko, T., Zhirosh, O., Johnston, D., & Gartsev, learning analytics in higher education.
S. (2017). On possibility of prediction Computers in Human Behavior, 89(October
of academic performance and potential 2017), 98–110. https://doi.org/10.1016/j.
improvements of admission campaign chb.2018.07.027
at IT university. IEEE Global Engineering
Education Conference, 862–866. Viloria, A., García Guliany, J., Niebles Núñez,
W., Palma, H. H., & Niebles Núñez, L.
Tan, T. Y., Jain, M., Obaid, T., & Nesbit, J. C. (2020). Data Mining Applied in School
(2020). What can completion time of Dropout Prediction. Journal of Physics,
quizzes tell us about students ’ motivations 1432, 12092. https://doi.org/10.1088/1742-
and learning strategies ? Journal of 6596/1432/1/012092
Computing in Higher Education, 32(2),
389–405. https://doi.org/10.1007/s12528- Vora, D. R., & Rajamani, K. (2019). A hybrid
019-09239-6 classification model for prediction of
academic performance of students : a big
Tasnim, N., Paul, M. K., & Sarowar Sattar, A. data application. Evolutionary Intelligence,
H. M. (2019). Performance Analysis of 0123456789. https://doi.org/10.1007/
Different Decision Tree Based Methods s12065-019-00303-9
for Identifying Drop out Students. 1st
International Conference on Advances Wang, Q., Wu, W., & Qi, Y. (2018). A Learning
in Science, Engineering and Robotics Analytic Model for Smart Classroom.
Technology 2019, ICASERT 2019, In Lecture Notes in Computer Science
2019(Icasert), 1–6. https://doi.org/10.1109/ (including subseries Lecture Notes in
ICASERT.2019.8934518 Artificial Intelligence and Lecture Notes
in Bioinformatics): Vol. 11268 LNCS.
Tenpipat, W., & Akkarajitsakul, K. (2020). Student Springer International Publishing. https://
Dropout Prediction : A KMUTT Case Study. doi.org/10.1007/978-3-030-01298-4_19
International Conference on Big Data
Analytics and Practices (IBDAP) Student. Wati, M., Indrawan, W., Widians, J. A., &
Puspitasari, N. (2018). Data mining
Tomasevic, N., Gvozdenovic, N., & Vranes, S. for predicting students’ learning result.
(2020). An overview and comparison of Proceedings of the 2017 4th International
supervised data mining techniques for Conference on Computer Applications
student exam performance prediction. and Information Processing Technology,
Computers and Education, 143(August CAIPT 2017, 2018-Janua, 1–4. https://doi.
2019), 103676. https://doi.org/10.1016/j. org/10.1109/CAIPT.2017.8320666
compedu.2019.103676
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6
A N A L I T I C A A C A D É M I C A : N U E V A S H E R R A M I E N T A S A P L I C A D A S A L A E D U C A C I Ó N · 1 5 8 ·
R E V I S T A B O L E T Í N R E D I P E 1 0 ( 3 ) : 1 3 7 - 1 5 8 - M A R Z O 2 0 2 1 - I S S N 2 2 5 6 - 1 5 3 6