Conference Agenda

This research is contextualized within the growing interest in optimizing student retention in higher education through the use of artificial intelligence-based learning analytics techniques, given their potential to personalize educational strategies and improve decision-making. Its objective was to determine the relationship between such analytics and student retention, using a quantitative approach and a non-experimental cross-sectional and correlational design. The methodology combined documentary analysis of institutional data—which revealed that most students are around 25 years old, take an average of seven courses, and perform well academically, although there was evidence of heterogeneity in academic workload and economic status—with surveys aimed at measuring retention and aspects of the learning environment, work responsibilities, and personal factors. The results highlighted that more than 98% of students have medium or high levels of retention, and a high positive correlation (ρ = 0.789, p < 0.05) was identified between artificial intelligence-based analytics and retention. In conclusion, the effective use of these tools translates into the identification of risks and more informed pedagogical decision-making, strengthening student retention.

This research investigates the transformational impact of Artificial Intelligence (AI) on corporate competitiveness within the framework of Industry 5.0, using a mixed-methods approach that combines the Resource-Based View (RBV) and Dynamic Capabilities Theory to tackle implementation issues particular to the industry. The study aims to concentrate on (1) measuring AI-induced productivity enhancements across various sectors, (2) analyzing human-AI cooperation frameworks, and (3) scrutinizing ethical governance structures, with a specific emphasis on Latin American settings. Methodologically, the research integrates qualitative case studies with quantitative surveys, using theme and regression analysis to corroborate results. The most important findings show that there are big differences across sectors: AI diagnoses can cut healthcare costs by 35%, whereas retail needs hybrid human-AI models to work best (15% benefits), and better governance frameworks can cut bias incidences by 58%. The conclusions stress that AI may be both a strategic resource and an adaptable capacity, depending on the culture of the business and the needs of the industry. Recommendations stress the need for tiered AI deployment roadmaps for Small and Medium-sized Enterprises (SMEs), ethical oversight committees, and initiatives to retrain workers. The subsequent study needs to investigate the long-term effects of AI implementation in circular economic transitions and culturally tailored governance frameworks, therefore filling the voids in studies concerning developing economies. This study connects global theoretical frameworks with regional empirical evidence, giving policymakers and practitioners useful information that fits with relevant research that balances technological innovation with socioeconomic equity.

Modern agriculture has to face a large number of problems due to the increase of crop diseases, affecting both productivity and economic lines of social groups in rural markets. This paper proposes a mobile application, based on the use of self-organizing neural networks (SOM, Self-Organizing Maps), for the automatic diagnosis of banana leaf diseases. The application allows capturing images from a mobile device (Android), processing them using image processing techniques and classifying them without the need for large volumes of labeled data. Unlike the other approaches such as convolutional neural networks (CNNs), the SOM method reduces computational demands, making it ideal for resource-constrained areas. The model was trained and validated using a database with real images of banana leaves affected by diseases such as Sigatoka, Cordana or Pestalotiosis. The results obtained show a high accuracy of the system, thus validating the effectiveness of the proposed approach for practical, sustainable and low-cost agricultural conditions.

This descriptive, non-experimental research project with a qualitative approach aimed to propose digital transformation strategies to reduce losses in the export supply chain of tangerines. A systematic literature review was conducted, along with the use of tools such as the Ishikawa diagram and expert interviews to identify the critical factors contributing to the problem. The findings revealed a loss rate of approximately 40% to 50%, primarily during the cultivation and harvesting stages. Additionally, through the use of MICMAC and Regnier’s Abacus tools, the most significant root cause identified was poor control of agroclimatic conditions—specifically, temperature and humidity. Using a SIPOC Turtle Diagram and a conceptual model, the study proposed an integrated system of temperature and humidity sensors during the cultivation stage. This solution demonstrated a reduction in tangerine losses by 10% to 15% and an economic benefit of 3 million dollars. The study presents a viable, adaptable, and cost-effective solution that not only reduces losses but also enhances the competitiveness of the tangerine export sector by improving fruit quality through the integration of technology and technical training.

The objective of this research was to compare the performance of Gemini and Copilot in solving multiple-choice questions, interpreting texts and images, for the entrance exams of a prestigious Peruvian university across its various faculties over the past three years.

This study analyzed 838 questions, of which 83 were analyzed as images. The overall results indicate a higher proportion of correct answers for Copilot, at 75% (627/838) versus 67% (561/838) for Gemini. The performance of both AIs was significantly lower in image analysis, with correct answers of 36.1% (30/83) for Gemini and 39.8% (33/83) for Copilot.

In conclusion, these findings highlight the need to improve accuracy in image processing, as well as the importance of understanding its current limitations to optimize its performance and integration into the academic field.

This study analyzes the role of internal controls in the prevention of money laundering within digital banking platforms

This study examines the key factors that increase football players’ risk of injury, considering physical, biomechanical, psychological, and contextual variables. Identified risk factors include prior injury history, neuromuscular fatigue, biomechanical asymmetries, inadequate training load, age, playing position, psychological stress, and adverse environmental conditions. Advanced tools using Artificial Intelligence (AI) and Big Data are reviewed for their role in integrating these variables for injury prevention. Techniques include supervised algorithms (Random Forest, SVM, k-NN), deep neural networks (CNN, RNN), wearable sensors (IoT), integrated Big Data platforms, clustering methods, and explainable AI (XAI) models. These approaches outperform traditional methods by enabling real-time monitoring, data integration, dynamic adaptation, and individualized planning—achieving over 90% accuracy in injury prediction and reducing injury incidence by up to 30%. The study follows a systematic review methodology based on the PICO model and PRISMA protocol. It includes bibliometric and content analyses and offers a critical discussion on evidence gaps and practical implementation. Conclusions highlight main findings, acknowledge limitations, and provide recommendations for future research.