Bibliographic citations
Gomez, R., (2018). Modelo predictivo de gestión administrativa y deserción estudiantil en programa pre grado adulto trabajador de universidad privada de Lima Metropolitana, año 2017 [Tesis, Universidad Privada del Norte]. https://hdl.handle.net/11537/13723
Gomez, R., Modelo predictivo de gestión administrativa y deserción estudiantil en programa pre grado adulto trabajador de universidad privada de Lima Metropolitana, año 2017 [Tesis]. PE: Universidad Privada del Norte; 2018. https://hdl.handle.net/11537/13723
@mastersthesis{renati/514323,
title = "Modelo predictivo de gestión administrativa y deserción estudiantil en programa pre grado adulto trabajador de universidad privada de Lima Metropolitana, año 2017",
author = "Gomez Rios, Ruben Darío",
publisher = "Universidad Privada del Norte",
year = "2018"
}
ABSTRACT The main objective of this research was to determine the relationship between the predictive model of administrative management and student desertion in the pregraduate adult worker program at a private university of metropolitan Lima in 2017. The research followed a non-experimental design of the correlation level with a quantitative approach. The data mining technique was used to obtain information about the predictive model from the collection of various documentary records of the institution involved; a survey on the causes of student desertion was also applied to a sample made up of 344 students. The relationship of both study variables was then established and the general hypothesis was partially verified, since there is significant evidence at the level of the average risk factor of accumulated lower grades, but linked to a high number of students enrolled in engineering courses with a high failing level. The results of the quantitative indicators of the risk factor of academic data and of student desertion, evidence that the number of approved credits accumulated (r = -0.140; p = 0.010 <0.05) has a significant relationship with the dropout of students from pre-program adult worker and, since the coefficient is negative, the relationship is inverse, that is, the lower the number of approved credits accumulated, the greater the probability of dropping out. On the other hand, it was found that the average risk of dropping out in the faculty of engineering career, is the highest reaching 73.9%, while law has the lowest desertion at 50%. It can be established that the predictive model analyzed initially shows the problems of desertion and that it needs to implement strategies to address the risk factors linked to career guidance such as the inappropriate choice of career, the distribution of personal time for studies. In many cases, the working student does not have an optimum time management for studying and other responsibilities; that is, they might enroll in to many courses in a given semester getting low grades or even failing. KEYWORDS: predictive model, student desertion, data mining, correlational study.
This item is licensed under a Creative Commons License