Sistema de predicción de rendimiento académico para segundo grado de primaria basado en machine Learning
Average rating
Cast your vote
You can rate an item by clicking the amount of stars they wish to award to this item.
When enough users have cast their vote on this item, the average rating will also be shown.
Star rating
Your vote was cast
Thank you for your feedback
Thank you for your feedback
Issue Date
2024-02-20Keywords
Predicción del rendimiento académicoInteligencia artificial
Random forest
Educación primaria
Computación en la nube
Academic performance Prediction
Artificial intelligence
Random forest
Primary education
Cloud computing
Metadata
Show full item recordOther Titles
ACADEMIC PERFORMANCE PREDICTION SYSTEM OF THE 2ND GRADE ELEMENTARY STATE SCHOOL STUDENTS IN THE SOUTH OF METROPOLITAN LIMA USING THE RANDOM FOREST ALGORITHMDOI
http://hdl.handle.net/10757/673841Abstract
En la actualidad, la educación en el Perú presenta diversas deficiencias que perjudican a los alumnos de educación básica y que, de no mitigarse a tiempo, puede desencadenar en escenarios difíciles de controlar. Se ha demostrado que, en la última EM tomada en el año 2022, menos del 40% y 20% de estudiantes del 2do grado de primaria lograron un puntaje satisfactorio en lectura y matemáticas, respectivamente, lo cual demuestra que existe una grave deficiencia en el rendimiento académico a pesar de todas las políticas aplicadas por el estado. En varios estudios se ha detectado que existen diversos factores que son influyentes en el rendimiento académico de los estudiantes, asimismo, algunos de estos han demostrado ser fuertes predictores del desempeño académico. Existen varios algoritmos o técnicas los cuales, a partir de estos factores, pueden predecir el rendimiento académico con el fin de brindar una herramienta a las autoridades educativas para que puedan tomar mejores decisiones en base a esta nueva información. En este trabajo se han tomado como objetos de estudio a dos colegios de la zona sur de Lima, obteniendo así una muestra de 103 estudiantes a partir de un instrumento validado por especialistas. Luego, se procedió a construir un sistema de predicción del rendimiento académico utilizando el Random Forest, el cual nos brindó una exactitud del 71.26% a partir de una validación cruzada de 5 etapas, lo cual es un buen indicador que el sistema podrá ser de utilidad para los directores de nuestros objetos de estudio.Currently, education in Peru has various deficiencies that harm basic education students and that, if not mitigated in time, can lead to scenarios that are difficult to control. It has been shown that, in the last SE taken in 2022, less than 40% and 20% of students in the 2nd grade of primary school achieved a satisfactory score in reading and mathematics, respectively, which shows that there is a serious deficiency in the academic performance despite all policies enforced by the state. In several studies it has been detected that there are several factors that are influencing the academic performance of students, likewise, some of these have been shown to be strong predictors of academic performance. There are several algorithms or techniques which, based on these factors, can predict academic performance to provide a tool to educational authorities so that they can make better decisions based on this latest information. In this work, two schools in the southern area of Lima have been taken as study objects, thus obtaining a sample of 103 students from an instrument validated by specialists. Then, we proceeded to build an academic performance prediction system using the Random Forest, which gave us an accuracy of 71.26% from a cross-validation of 5 stages, which is a good indicator that the system may be useful. for the directors of our objects of study.
Type
info:eu-repo/semantics/bachelorThesisRights
Attribution-NonCommercial-ShareAlike 4.0 Internationalinfo:eu-repo/semantics/openAccess
Language
spaae974a485f413a2113503eed53cd6c53
http://hdl.handle.net/10757/673841
Scopus Count
Collections
Except where otherwise noted, this item's license is described as Attribution-NonCommercial-ShareAlike 4.0 International