Julien Brito Ballester

Julien Brito Ballester

Auto-generated profile, based on publicly available information

Julien Brito Ballester

Universidad Europea del Atlántico

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 February 2023 in International Journal of Emerging Technologies in Learning (iJET)
Verified
Journal Article
Open access
PDF file
CVCarmen Lilí Rodríguez Velasco
Carmen Lilí Rodríguez Velasco
EVEduardo García Villena
Eduardo García Villena
JBJulien Brito Ballester
Julien Brito Ballester
FPFrigdiano Álvaro Durántez Prados
Frigdiano Álvaro Durántez Prados
EAEduardo Silva Alvarado
Eduardo Silva Alvarado
JAJorge Crespo Alvarez
Jorge Crespo Alvarez
The purpose of this research article was to contrast the benefits of the optimal probability threshold adjustment technique with other imbalanced data processing techniques, in its application to the prediction of post-graduate students’ late dropout from distance learning courses in two universities in the Ibero-American space. In this context, the optimization of the Logistic Regression, Random Forest, and Neural Network classifiers, together with different techniques, attributes, and algorithms (Hyperparameters, SMOTE, SMOTE_SVM, and ADASYN) resulted in a set of metrics for decision-making, prioritizing the reduction of false negatives. The best model was the Neural Network model in combination with SMOTE_SVM, obtaining a recall index of 0.75 and an f1-Score of 0.60. Likewise, the robustness of the Random Forest classifier for imbalanced data was demonstrated by achieving, with an optimal threshold of 0.427, very similar metrics to those obtained by the consensus of the three best models found. This demonstrates that, for Random Forest, the optimal prediction probability threshold is an excellent alternative to resampling techniques with different optimal thresholds. Finally, it is hoped that this research paper will contribute to boost the application of this simple but powerful technique, which is highly underrated with respect to data resampling techniques for imbalanced data.

28 March 2023 in MLS Educational Research
Verified
Journal Article
Open access
PDF file
IAIrma Domínguez Azpíroz
Irma Domínguez Azpíroz
MVMónica Gracia Villar
Mónica Gracia Villar
JBJulién Brito Ballester
Julién Brito Ballester
CVCarmen Lilí Rodríguez Velasco
Carmen Lilí Rodríguez Velasco
Emmanuel Soriano FloresEmmanuel Soriano Flores
Emmanuel Soriano Flores
The purpose of this research article was to perform a classification based on neural networks to predict the level of satisfaction of a sample of graduates, corresponding to different graduate programs in the health area of a Latin American educational institution under an e-learning methodology. To this end, a Likert scale questionnaire model was instrumented which, after being validated, had a reliability of 0.791. Likewise, the average global satisfaction index of the graduates was 2.66/4, witha better score in the section on logistics of materials and in the management and technical support of the virtual campus, while the lowest scores referred to aspects related to extra-center communication and the facilities offered by the institution for the improvement of the participant's economic and social context. Finally, the probabilistic classification and prediction algorithm of the neural network obtained an accuracy of 96.8%, indicating an excellent degree of model fit. The methodology followed and the rigor in determining the validity and reliability of the instrument, as well as the subsequent analysis of the results, endorsed by the review of the documented information, suggest that the instrument can be applied to other multidisciplinary programs for decision making with guarantees in the educational field.