Construcción e implementación de un modelo para predecir el rendimiento académico de estudiantes universitarios mediante el algoritmo Naïve Bayes

Páez, Andrés Rico; Ramírez, Nora Diana Gaytán; Guzmán, Daniel Sánchez

doi:10.32870/dse.v0i19.509

Cited by 3 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Los predictores académicos constituyen un tópico importante relativo al rendimiento académico. De acuerdo con Rico et al (2019), el modelo predictivo identifica los factores que más influyen en él y permite a los maestros diseñar estrategias de prevención e identificar a los estudiantes que son vulnerables al fracaso. Es importante subrayar que el rendimiento académico está relacionado con los entornos de aprendizaje; tal como lo plantean Akçapınar et al (2019), los datos de interacción de los estudiantes en un entorno de aprendizaje en línea se utilizaron para investigar si el rendimiento académico de los estudiantes al final del trimestre podría predecirse en las primeras semanas.…”

Section: Resultsunclassified

Factores asociados al desempeño académico universitario: tendencias geográficas, temporales y temáticas

et al. 2021

View full text Add to dashboard Cite

El objetivo de esta revisión bibliográfica fue identificar los factores que inciden en el desempeño académico universitario. La metodología consistió en llevar a cabo una revisión sistemática de la literatura en Web of Science (incluye Scielo) y Scopus, con ayuda del gestor bibliográfico Citavi 6 y el software de análisis de datos cualitativos MaxQDA 2020. La búsqueda reportó 1491 artículos que incluyen las categorías academic performance, academic achievement, university students. De los 1491 se excluyó una tercera parte, según los criterios socioeconómicos, culturales y educativos. Se concluyó que el rendimiento académico es un fenómeno complejo asociado a factores psicológicos y pedagógicos; sin embargo, en los últimos años se observa un auge de los discursos y argumentos provenientes de la psicología y la administración en detrimento de los análisis de los factores sociales y económicos.

show abstract

Section: Resultsunclassified

Factores asociados al desempeño académico universitario: tendencias geográficas, temporales y temáticas

et al. 2021

View full text Add to dashboard Cite

show abstract

Prediction of University-Level Academic Performance through Machine Learning Mechanisms and Supervised Methods

Bravo

Nieves-Pimiento²,

Gonzalez-Guerrero³

2022

Ing.

View full text Add to dashboard Cite

Context: In the education sector, variables have been identified which considerably affect students’ academic performance. In the last decade, research has been carried out from various fields such as psychology, statistics, and data analytics in order to predict academic performance. Method: Data analytics, especially through Machine Learning tools, allows predicting academic performance using supervised learning algorithms based on academic, demographic, and sociodemographic variables. In this work, the most influential variables in the course of students’ academic life are selected through wrapping, embedded, filter, and assembler methods, as well as the most important characteristics semester by semester using Machine Learning algorithms (Decision Trees, KNN, SVC, Naive Bayes, LDA), which were implemented using the Python language. Results: The results of the study show that the KNN is the model that best predicts academic performance for each of the semesters, followed by Decision Trees, with precision values that oscillate around 80 and 78,5% in some semesters. Conclusions: Regarding the variables, it cannot be said that a student’s per-semester academic average necessarily influences the prediction of academic performance for the next semester. The analysis of these results indicates that the prediction of academic performance using Machine Learning tools is a promising approach that can help improve students’ academic life allow institutions and teachers to take actions that contribute to the teaching-learning process.

show abstract

Rendimiento académico universitario en países latino americanos bajo la neurocomputación biológica

Jiménez-Galán

Falcone-Treviño

Tinajero-Mallozzi

et al. 2019

JUM

View full text Add to dashboard Cite

First, that it can be identified if academic performance and psychosocial skills, under the Latin American identity in the university concept in Argentines, Peruvians, Costa Ricans and Mexicans, increase for their students, considering the improvement in the development of the academic study; second, to analyze that academic achievement when considering biological neurocomputing allows to identify the degree of anxiety in students; third, measure the different indicators between social skills and academic averages among students. Through its multicenter observational design focused on biological neurocomputing, a measuring instrument was used on the MEDMAR scale, with a finite sample of the student universe of 1500, with different school environments in the universities of the National University of Rosario (Argentina), National University Mayor of San Marcos de Lima (Peru), University of Costa Rica (Costa Rica), University of Guadalajara (Mexico), University of Aguascalientes (Mexico) and Autonomous University of Tamaulipas (Mexico) in 2018. With indicators on the affective / emotional. The academic performance and behavior of the students, it was detected that 20% of students with lack of motivation for their learning. Situations of computational neurobiological character were defined with interaction towards educational programs, when managing the optimal academic performance and the constant lack of interest in the new knowledge to acquire with data of internal consistency, test-retest reliability and concurrent validity.

show abstract

Construcción e implementación de un modelo para predecir el rendimiento académico de estudiantes universitarios mediante el algoritmo Naïve Bayes

Abstract: Construcción e implementación de un modelo para predecir el rendimiento académico de estudiantes universitarios mediante el algoritmo Naïve Bayes Construction and implementation of a model to predict the academic performance of university students using the Naïve Bayes algorithm

Cited by 3 publications

References 11 publications

Factores asociados al desempeño académico universitario: tendencias geográficas, temporales y temáticas

Factores asociados al desempeño académico universitario: tendencias geográficas, temporales y temáticas

Prediction of University-Level Academic Performance through Machine Learning Mechanisms and Supervised Methods

Rendimiento académico universitario en países latino americanos bajo la neurocomputación biológica

Contact Info

Product

Resources

About