Citas bibligráficas
Jesus, A., Jimenez, O. (2024). Modelo de análisis predictivo para el monitoreo de la deserción estudiantil aplicando machine learning en la educación superior universitaria del Perú [Tesis, Universidad Peruana de Ciencias Aplicadas (UPC)]. http://hdl.handle.net/10757/674924
Jesus, A., Jimenez, O. Modelo de análisis predictivo para el monitoreo de la deserción estudiantil aplicando machine learning en la educación superior universitaria del Perú [Tesis]. PE: Universidad Peruana de Ciencias Aplicadas (UPC); 2024. http://hdl.handle.net/10757/674924
@misc{renati/419690,
title = "Modelo de análisis predictivo para el monitoreo de la deserción estudiantil aplicando machine learning en la educación superior universitaria del Perú",
author = "Jimenez Ramirez, Omar Antonio Hernan",
publisher = "Universidad Peruana de Ciencias Aplicadas (UPC)",
year = "2024"
}
This project analyzes the main factors of university dropout and proposes a predictive analysis model applying Machine Learning to detect early dropout cases. Currently, student dropout is a problem that not only affects the student, but also the families, university and society. With the support of machine learning, the main purpose of this project is to identify desertion cases in order to help universities to act as soon as possible. After analyzing similar research, we prepared a benchmarking of potentially applicable algorithms. Finally, the project develops a predictive analysis model applying the Random Forest (RF) algorithm. For the design of the model, a total of fourteen (14) variables were defined pertaining to student demographics, pre-university education and admission of the student, family environment, social integration and academic performance of the student, and cognitive and emotional variables of the student.
Este ítem está sujeto a una licencia Creative Commons Licencia Creative Commons