Adaptive business intelligence and its Predictive application on Taxonomic patterns of desertion
DOI:
https://doi.org/10.25044/25392190.902Keywords:
data mining, business intelligence, predictive, adaptive.Abstract
The variables that arise from the databases of a National University of Argentina, favor the analysis and application of a methodology of Adaptive Business Intelligence, by which, applying the appropriate filters in a methodological way, as it is exposed in the present work, will allow Finding students at risk of defecting and doing preventive work on them. There are socio-psychometric, economic and cultural data, in addition to physical elements that have to be taken into consideration by relating them to the finality of studies of the subjects evaluated. Emerges from there, a predictive learning model that classifies the causalities of desertion. Finally, this knowledge can be exploited to develop the application in any programming language, so that it takes advantage of such knowledge, with use in new subjects and their data. By virtue of this, the main advantages obtained from the predictive capabilities on the data of the case are exposed.Downloads
References
Alom, B. M., & Courtney, M. (2018). Educational Data Mining: A Case Study Perspectives from Primary to University Education in Australia.
Binstock Georgina. (2005). Carreras truncadas. UNICEF. Recuperado de https://www.unicef.org/argentina/spanish/Carrerastruncadas(1).pdf
Breiman, L. (2017). Classification and regression trees. Routledge.
Cios, K. J., Pedrycz, W., Swiniarski, R. W., & Kurgan, L. A. (2007). Data mining: a knowledge discovery approach. Springer Science & Business Media.
Eckert, K. B., & Suénaga, R. (2015). Análisis de deserciónpermanencia de estudiantes universitarios utilizando técnica de clasificación en minería de datos. Formación universitaria, 8(5), 03-12.
Educ.ar El portal educativo argentino. (2017). Recuperado de http://portal.educ.ar/noticias/educacion-ysociedad/
desercion-escolar.php
Farías, M., Fiol, D, Kit, I. Melgar, S. (2007). Todos pueden aprender - Propuestas para superar el fracaso escolar. UNICEF - Oficina de Argentina.
Michalewicz, Z., Schmidt, M., Michalewicz, M., & Chiriac, C. (2006). Adaptive business intelligence (pp. 37-46). Springer Berlin Heidelberg.
Peral, J., Maté, A., & Marco, M. (2017). Application of data mining techniques to identify relevant key performance indicators. Computer Standards & Interfaces, 54, 76-85.
Shmueli, G., Bruce, P. C., Yahav, I., Patel, N. R., & Lichtendahl Jr, K. C. (2017). Data Mining for Business Analytics: Concepts, Techniques, and Applications in R. John Wiley & Sons.
Slater, S., Joksimović, S., Kovanovic, V., Baker, R. S., & Gasevic, D. (2017). Tools for educational data mining: A review. Journal of Educational and Behavioral Statistics, 42(1), 85-106.
Una Metodología para el Desarrollo de Aplicaciones Autoadaptativas basada en Business Intelligence. Aplicación en Medicina. (2012). (Tesis para optar a la titulación de postgrado correspondiente a la Maestría en Ingeniería de Software).
Villegas-Ch, W., & Luján-Mora, S. (2017, March). Analysis of data mining techniques applied to LMS for personalized education. In World Engineering Education Conference (EDUNINE), IEEE (pp. 85-89). IEEE.
Watson, H. J., & Wixom, B. H. (2007). The current state of business intelligence. Computer, 40(9)