Early prediction of student performance in online programming courses is essential for implementing timely interventions to enhance academic outcomes. This study aimed to predict academic success by comparing four machine learning models: Logistic Regression, Random Forest, Support Vector Machine (SVM), and Neural Network (Multilayer Perceptron, MLP). We analyzed data from the Moodle Learning Management System (LMS) and external factors of 591 students enrolled in online object-oriented programming courses at the Universidad Estatal de Milagro (UNEMI) between 2022 and 2023. The data were preprocessed to address class imbalance using the synthetic minority oversampling technique (SMOTE), and relevant features were selected based on Random Forest importance rankings. The models were trained and optimized using Grid Search with cross-validation. Logistic Regression achieved the highest Area Under the Receiver Operating Characteristic Curve (AUC-ROC) on the test set (0.9354), indicating strong generalization capability. SVM and Neural Network models performed adequately but were slightly outperformed by the simpler models. These findings suggest that integrating LMS data with external factors enhances early prediction of student success. Logistic Regression is a practical and interpretable tool for educational institutions to identify at-risk students, and to implement personalized interventions.

Early prediction of academic performance is vital for reducing attrition in online higher education. However, existing models often lack comprehensive data integration and comparison with state-of-the-art techniques. This study, which involved 2,225 engineering students at a public university in Ecuador, addressed these gaps. The objective was to develop a robust predictive framework by integrating Moodle interactions, academic history, and demographic data using SMOTE for class balancing. The methodology involved a comparative evaluation of seven base learners, including traditional algorithms, Random Forest, and gradient boosting ensembles (XGBoost, LightGBM), and a final stacking model, all validated using a 5-fold stratified cross-validation. While the LightGBM model emerged as the best-performing base model (Area Under the Curve (AUC) = 0.953, F1 = 0.950), the stacking ensemble (AUC = 0.835) did not offer a significant performance improvement and showed considerable instability. SHAP analysis confirmed that early grades were the most influential predictors across top models. The final model demonstrated strong fairness across gender, ethnicity, and socioeconomic status (consistency = 0.907). These findings enable institutions to identify at-risk students using state-of-the-art interpretable and fair models. These findings enable institutions to identify at-risk students using state-of-the-art, interpretable, and fair models, advancing learning analytics by validating key success predictors against contemporary benchmarks.

This study presents the preliminary validation of an integrated system that combines predictive analytics with an artificial intelligence (AI)-powered chatbot to address academic failure and dropout in higher education. The system leverages a high-performance Light Gradient Boosting Machine (LightGBM) predictive model, previously validated to achieve state-of-the-art accuracy (Area Under the Curve (AUC) = 0.953), to identify at-risk students at an early stage. The intervention component is an AI chatbot powered by the GPT-4o-mini large language model (LLM), which operates via WhatsApp® to deliver personalized, real-time support using context-aware semantic search. A pilot implementation with 108 students demonstrated the system’s viability, with 39 at-risk students identified and engaged in 742 interactions. Key operational metrics included a high student response rate of 89.7%, an initial intervention time of 6.6 seconds (s), and an average chatbot response time of 12.9 s. These findings confirm the technical feasibility of fusing machine learning with conversational AI to create timely, scalable, and personalized interventions, establishing a foundation for improving student success and retention in the future.

This article examined digital gaps and their impact on the cultural exclusion of Ecuadorian youth aged 20 to 24 in Zone 5, composed of the provinces of Guayas, Los Ríos, Bolívar, Santa Elena, and Galápagos. Using a quasi-experimental design and a quantitative approach, data were collected and compared between two groups differentiated by their level of connectivity and pedagogical mediation. The sample consisted of 400 young people, equally distributed between both groups. A structured questionnaire was applied to assess dimensions such as digital cultural capital, participation in online cultural practices, use of platforms, and barriers to cultural digital appropriation. The results showed that the group with stable connectivity and training in digital skills presented higher levels of technological self-efficacy, participation in digital cultural communities, and production of symbolic content. In contrast, the other group exhibited limitations in both access (unstable mobile connections and basic devices) and the ability to leverage cultural opportunities in the digital environment. Statistical tests revealed significant differences between the groups in all measured dimensions (p < 0.01), with moderate to high effect sizes. It was concluded that digital exclusion among youth is not only technical but also symbolic, cultural, and educational. Furthermore, it was proposed that public policies should incorporate critical training, territorial support, and cultural inclusion, moving beyond a merely infrastructural paradigm.

Este proyecto se centra en el campo de la seguridad en Servidores Virtuales en los entornos Cloud. En concreto, se estudia la seguridad a Infraestructura como Servicio (IaaS). Se estudia el caso específico de la minimización del riesgo relacionado a la seguridad al instalar máquinas virtuales en servidores físicos. Se analiza y describe como una máquina virtual vulnerable, puede comprometer a las otras máquinas virtuales vecinas e inclusive al servidor físico. En este estudio se propone un nuevo método para cuantificar el riesgo de seguridad para las máquinas virtuales. Los resultados arrojados por este método son tomados en cuenta para decidir la ubicación de un nuevo servidor virtual en un servidor físico con el fin de maximizar la seguridad. En este documento se proporciona una guía de buenas prácticas de seguridad centrada en la seguridad del servidor virtual.

This exploratory study aimed to analyze the perceptions of students and faculty members regarding the impact of virtual tutoring and the educational chatbot “TutoBot” on academic retention in the Software Engineering program at the University of Guayaquil. A mixed-methods approach was employed, comprising a qualitative phase (interviews and document analysis) and a quantitative phase (surveys administered to 100 students and 5 faculty members). The findings indicate that the integration of virtual tutoring and the chatbot enhances students' perception of academic support and is associated with a reduced intention to drop out. Statistical correlations revealed significant associations between tutorial support and student engagement. Although the chatbot was perceived as a valuable support tool, it does not substitute for human tutors. The study concludes that this integrated strategy strengthens student retention, provided it is supported by adequate faculty training, pedagogical planning, and technological adaptation. It is recommended to replicate this model in other academic programs and to implement improvements in the chatbot's design.