IMPLEMENTATION OF MACHINE LEARNING TECHNIQUES AND CREATION OF AN ARTIFICIAL NEURAL NETWORK FOR THE PREDICTION OF THE ACADEMIC PERFORMANCE OF STUDENTS IN UNIVERSITY ENVIRONMENTS THAT USE E-LEARNING AND STREAMING

Aug 2, 2026

Upload by Quinn

Implementation compares machine learning models—Random Forest, Xtreme Boosting Gradient (XGBoost), Support Vector Machine, K-Nearest-Neighbor, and Logistic Regression—and builds an artificial neural network to predict low academic performance of university students using e-learning and streaming. The study frames e-learning as a key alternative accelerated by the COVID-19 pandemic and examines whether virtual teaching affects performance compared with face-to-face instruction, considering factors such as gender, number of children, sex, age, and study type. Classification metrics show XGBoost accuracy at 78.4%, while the ANN achieves 82.4%, supporting ANN for accurate and scalable prediction.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages17

Reading Time43 min

AccessFree to download

Introduction

Educational context and e-learning adoption

Research motivation and variables affecting performance

IMPLEMENTATION OF MACHINE LEARNING TECHNIQUES AND CREATION OF AN ARTIFICIAL NEURAL NETWORK FOR THE PREDICTION OF THE ACADEMIC PERFORMANCE OF STUDENTS IN UNIVERSITY ENVIRONMENTS THAT USE E-LEARNING AND STREAMING | Teresa Santamaría-Lopez1 , Darwin Patiño-Perez2 , Vicente González-Ruiz3 y Leila Flores-Carvajal4
Universidad de Guayaquil. 1 Facultad de Filosofía, 2 Facultad de Ciencias Matemáticas y Física 4 Facultad de Administración. Av. Delta, s/n y Av. Kennedy-090514 Guayaquil, Guayaquil (Ecuador) .
3 Universidad de Almería. Edificio de Matemáticas e Informática. Oficina 1.53. Carretera Sacramento, s/n-04120 La Cañada de San Urbano, Almería (España) . | | --- | | DOI: [https://doi.org/10.6036/10760](https://doi.org/10.6036/10760 | Received:)[ | Received:](https://doi.org/10.6036/10760 | Received:) 14/nov/2022 • Reviewing: 21/nov/2022 • Accepted: 01/feb/2023 | | To cite this article: SANTAMARÍA-LOPEZ, Teresa; PATIÑO-PEREZ, Darwin; GONZALES-RUIZ, Vicente; FLORES-CARVAJAL, Leila. IMPLEMENTATION OF MACHINE LEARNING TECHNIQUES AND CREATION OF AN ARTIFICIAL NEURAL NETWORK FOR THE PREDICTION OF THE ACADEMIC PERFORMANCE OF STUDENTS IN UNIVERSITY ENVIRONMENTS THAT USE E-LEARNING AND STREAMING. DYNA. May – June 2023. vol. 98, n.3, pp. 282-287. DOI: [https://doi.org/10.6036/10760](https://doi.org/10.6036/10760) | | ABSTRACT:
This work describes the implementation of machine learning (ML) techniques: Random Forest, Xtreme Boosting Gradient, Support Vector Machine, K-Nearest-Neighbor and Logistic Regression as well as the creation of an artificial neural network (ANN), which were compared to determine the technique that can learn to predict with greater accuracy, the low academic performance of university students, to improve the mechanisms of e-learning and streaming that help them raise academic performance. The e-learning methodology was established for the first time in the late 1990s, however, since the Covid-19 pandemic, it has established itself asthe best alternative to traditional education, placing it as a benchmark worldwide. One of the concerns in the university environment where this study was carried out is to be able to determine the impact that virtual teaching has had compared to face-to-face teaching, since there are factors (gender, number of children, sex, age, type of study) that could influence the academic performance of students. Using the classification metrics within the comparative process, it was determined that among the implemented ML techniques, the XGBoost reached 78.4% accuracy, but was surpassed by the artificial neural network (ANN) that learned to predict with 82.4% . of accuracy. Due to the above, the use of the artificial neural network is recommended for the prediction of the academic performance of university students since, in addition, with its massive predictions can be made due to its high processing capacity.
Key Words: e-learning, covid19, streaming, academic performance, machine learning, artificial neural networks, | RESUMEN:
Este trabajo se describe la implementación de las técnicas de machine learning (ML): Random Forest, Xtreme Boosting Gradient, Suport Vector Machine, K-Nearest-Neighbor y Logistic Regression, así como la creación de una red neuronal artificial (ANN), que fueron comparadas para determinar la técnica que puede aprender a predecir con mayor exactitud, el bajo rendimiento académico de estudiantes universitarios, para mejorar los mecanismos de e-learning y streaming que les ayudea elevar el rendimiento académico. La metodología e-learning fue instaurada por primera vez a finales de los noventa, sin embargo, apartir de la pandemia del Covid-19, se estableció como la mejor alternativa a la educación tradicional ubicándola como un referente anivel mundial. Una de las preocupaciones en el ambiente universitario donde se realizó este estudio, es poder determinar el impacto que hatenido la enseñanza virtual en comparación con la enseñanzapresencial, ya que exis

FAQs

Which machine learning techniques are compared in the study?

The study compares Random Forest, XGBoost (Xtreme Boosting Gradient), Support Vector Machine, K-Nearest-Neighbor, and Logistic Regression, and also develops an artificial neural network.

How does the artificial neural network perform compared with XGBoost?

XGBoost reaches 78.4% accuracy, while the ANN achieves 82.4% accuracy in predicting low academic performance.

What factors are considered when evaluating academic performance in university environments?

The study considers factors that may influence performance, including gender, number of children, sex, age, and the type of study modality.

Aug 2, 2026

Upload by Quinn