Conference Agenda

Cyber threats and risks associated with digital security have increased considerably in the banking sector, driving the need to adopt new technologies that allow detecting and mitigating potential attacks. This review aims to identify the most widely used machine learning models against malware detection. Method: 194 original articles related to the subject were analyzed, of which only 27 met the inclusion criteria for the final review. Additionally, a dynamic analysis was used to examine the performance of the algorithms in real and simulated scenarios. It was evident that Machine Learning models, particularly supervised learning models such as neural networks, support vector machines, and random forest algorithms, have achieved promising results in the early detection of malware, allowing for a faster and more accurate response to potential cyber threats. The integration of Machine Learning into banking cybersecurity has generated significant advances in the identification and control of malicious attacks, provided that there is adequate data quality, constant updating of the models, and proper coordination with existing defense systems. Therefore, it is concluded that the use of these technologies, beyond their technical capacity, also represents an opportunity to strengthen the culture of prevention and digital resilience within the financial environment

The current study investigates the impact of the integration of the Internet of Things (IoT) on improving academic performance in higher education students during the years 2019-2023. A systematic literature review is used to address the search problem and 26 relevant studies are identified. Methods include bibliometric data collection and qualitative compilation of results. Findings show a wide variety of tools and effects derived from the implementation of IoT in educational settings, including increased interaction between students and teachers, better resource management, and an enriched educational experience. It is the results of practical implications that are discussed, such as the need for increased support for technological infrastructure and training of teaching staff. Furthermore, the contribution of the study to understanding the emerging role of technology in higher education is highlighted. In conclusion, the importance of exploiting the opportunities offered by IoT to modernize teaching and learning in the university environment is underlined, while addressing challenges such as security and technological acceptance.

The digital transformation of the financial sector has been rapidly accelerated by the strategic integration of artificial intelligence (AI) technologies, which have demonstrated high potential to enhance operational efficiency, customer experience, and decision-making processes. This study presents a systematic review of scientific literature published between 2019 and 2025, aiming to analyze the development and application of AI in banking, insurance, fintech, and investment sectors, while identifying technological patterns, ethical implications, regulatory challenges, and research gaps. The PRISMA 2020 protocol was applied for the selection process, along with thematic and categorical analysis, and tools such as VOSviewer and RobVis for data visualization. The review includes 32 high-impact studies retrieved from major databases such as Scopus, Web of Science, Redalyc, and SpringerOpen. The findings reveal that machine learning, natural language processing (NLP), and deep neural networks are the most widely used technologies, primarily for process automation, fraud detection, and predictive analytics. Significant advances were identified in financial inclusion through intelligent platforms, although challenges remain concerning cybersecurity, algorithmic bias, and the absence of adaptive regulatory frameworks. A predominance of European and Latin American quantitative studies was observed, enabling comparative lessons on implementation. This study contributes to structuring the scattered knowledge on AI in finance and proposes future research lines to promote its ethical and sustainable integration into the global financial system.

In recent years, the application of Machine Learning (ML) and Deep Learning (DL) techniques in sales forecasting has gained significant relevance as a strategic tool to optimize business processes and decision-making. This Systematic Literature Review (SLR) aims to identify the most widely used models and assess their effectiveness in sales estimation across various commercial settings. Following the PRISMA methodology, five academic articles published between 2022 and 2025 were analyzed. The results indicate that the most commonly employed models are Random Forest, XGBoost, LSTM, and CNN, all of which outperform traditional methods such as ARIMA and linear regression. It is noteworthy that DL techniques and hybrid models achieve R² values above 90% and mean absolute percentage errors (MAPE) below 10%, confirming their effectiveness in multivariable and dynamic contexts.

EEG (Electroencephalographic) signal processing and brain mapping face significant challenges due to low signal-to-noise ratio, inter-subject variability, and high data dimensionality. These limitations hinder the identification of neurophysiological patterns and reduce their clinical utility, especially in contexts requiring high diagnostic precision. Addressing these issues requires advanced preprocessing techniques, artifact removal, and spatial localization of brain activity, which adds complexity to the analysis. This study presents an automated pipeline developed in Python to process multichannel EEG signals (64 channels), acquired using the Neuroscan system and Curry Neuroimaging Suite 7 software in resting-state patients with eyes open. The tool enables data loading, visualization, cleaning, analysis, and export, facilitating its use by researchers and clinical professionals. Its main contribution lies in improving EEG data quality through automated procedures that reduce noise without compromising the original signal, thus supporting more accurate and reliable interpretation in clinical and neuroscientific applications.

The following systematic review discusses the effectiveness of ITIL, COBIT, and ITSM frameworks in standardizing IT services in hospital settings. The objective was to compare how these management frameworks contribute to improving incident management, operational continuity and the perception of user quality in health institutions. 36 articles published between 2020 and 2025 were analyzed, selected using the PICOC technique and following the PRISMA methodology. The findings reveal that ITIL is the most adaptable framework in resource-constrained hospitals, achieving a 25% decrease in incident resolution times and a 60% increase in resolved tickets. COBIT showed strengths in governance and auditing, although with low adoption in rural areas due to its technical complexity. ITSM improved user perception, but with challenges in subjective aspects such as empathy. It is concluded that ITIL is the most viable option for contexts with limited infrastructure, while a hybrid integration with COBIT would be suitable for more complex systems. In addition, the need for more representative research in Latin America is highlighted, to more accurately evaluate the implementation of these in different contexts within a hospital center.