Sistema Regional de Información
en línea para Revistas Científicas de América Latina,
el Caribe, España y Portugal

This research analyzes the environment of the Fintech ecosystem and cryptocurrencies in Colombia, with a par-ticular focus on regulatory challenges and opportunities. A qualitative methodology is used to identify the regulatory challenges faced by these technologies and their impact on their adoption in the country. Additionally, the lack of adequate regulation for cryptocurrencies is addressed, which creates a climate of uncertainty that discourages investment and affects consumer protection. The need to develop a coherent and efficient regulatory framework that drives innovation, protects consumers and promotes responsible financial inclusion is underlined. The results in-dicate that, although Colombia has made significant prog-ress in the regulation of these technologies, important challenges persist, such as inequality in access to technolo-gy and education, regulatory fragmentation, and instabili-ty in data security. These obstacles are crucial to achieving a balanced and sustainable environment in the Colombian financial ecosystem.

The document shows an analysis carried out through Artificial Intelligence models to make comparisons in the predictions of investment portfolios in Mexico and the United States. ARIMA models were used for the prediction of time series in comparison with the multilayer perceptron neural network and particle swarm in the optimal portfolio selection. Markowitz's theory (1952) is also applied to identify the type of portfolio on the efficient frontier. The study shows that artificial intelligence can help in the design of better investment strategies in a given time. The document is limited by the fact that only the main companies from the aforementioned countries were taken, but the model can be replicated with larger samples even in other stock exchanges. Key words: Investment portfolios, Investment strategies, Artificial intelligence. Jel codes: G11, G12, G14

The article analyzes theoretically and critically the relationship between the Digital Economy (DE) and inspection in Mexico. It is based on a documentary review of some publications on the subject, such as those of the United Nations, the Organization for Economic Cooperation and Development, the European Union, and articles on the Internet. And, it builds a series of conceptualizations on ED, tax evasion, metaverse, significant economic presence, legislation and cybersecurity in Mexico, among others. A discussion and conclusions are also proposed, with the perspective of suggesting some legal-fiscal measures, to prevent the ED from promoting the informal economy and tax illicit activities, and trying to promote justice, equity and ethics, through tax collection, to promote a broad comprehensive democratic and participatory Tax Reform.

Credit risk assessment remains a critical challenge for financial institutions, as poor classification of borrowers can lead to significant financial losses. This study presents the development of a predictive credit risk model using machine learning algorithms applied to simulated financial data. The use of a synthetic dataset allows for the creation of realistic client profiles while preserving data privacy. The research compares the performance of several algorithms—Logistic Regression, Decision Trees, Random Forest, XGBoost, and Multilayer Perceptron—using metrics such as accuracy, recall, F1-score, and AUC-ROC. The models were trained using an 80/20 data split and validated with 5-fold cross-validation. XGBoost outperformed the other models, achieving 92% accuracy and strong recall, indicating its suitability for identifying high-risk individuals. The findings demonstrate that machine learning models, particularly ensemble and neural-based approaches, can significantly improve credit risk prediction compared to traditional methods. This has implications for financial decision-making processes, especially in institutions aiming to reduce default rates and optimize credit allocation strategies. The study also highlights challenges such as model interpretability and the need for validation on real-world datasets. Future work will focus on integrating explainable AI tools and testing the models with data from financial institutions.

Unless humans change their lifestyles, thousands of tons of carbon dioxide and chronic diseases caused by chemicals in products and their manufacturing processes that have been designed to date will continue to be the biggest environmental problem. Greenhouse gases (GHG) in the air such as carbon dioxide, methane, nitrous oxide, fluorinated gases and perfluorocarbons (ParEu, 2023) occupy the first place in global pollution (Núñez, C., 2023) and the effects of chemical substances harmful to health, such as pesticides, have caused chronic diseases and damage to water, land and air. Given the magnitude of the environmental problem in Mexico, and in response to international commitments such as the Kyoto Protocol (KP) and the Paris Agreement (PA) to mitigate climate change, tax instruments have been created for non-fiscal purposes, in Mexico through article 1, sections I and II, of the Law of Special Taxes on Production and Services (LIESPYS) with the purpose of modifying an action or behavior that is harmful to the environment derived from its extra-fiscal scope. The purpose of this article is to reflect (in general) on this precept, the generating fact, the interpretation of the norm through arguments, criteria and opinions of various authors, as well as its effectiveness and scope, hoping that, with the documentary methodology of a descriptive explanatory type, its imposition and the essence of its origin for which these instruments were created will be identified.

This article reviews and analyzes some of the key international documents and initiatives related to climate change, the environment, sustainable development, and disaster risk reduction, from the 1990s to the present day. The research revolves around in three periods: from the beginning of the 1990s to the year 2000, the first decade of the 21st century and, finally, from 2015, when the three post-2015 global agendas are approved: the Paris Agreement on climate change, the 2030 Agenda for Sustainable Development and the Sendai Framework for Disaster Risk Reduction. In addition, a brief description is made of the policies and actions implemented in recent years linked to climate change in countries, regions, and institutions that are consider particularly relevant. The article concludes that the actions taken against climate change at the international level have been evolving towards effective integrated management between the environment, sustainable development, and disaster risk reduction.

The province of San Antonio, Chile, is highly susceptible to tsunami risk and its Territorial Planning Instruments (TPIs) lack designated risk areas. Furthermore, in Chile, risk reduction through territorial planning is limited by the absence of standardized methodologies for risk zoning and the exclusive focus on hazards, hindering the implementation of effective measures. In response to this, a methodology was proposed that combines hazards and vulnerability using publicly available data, employing the SoVI method adjusted with critical infrastructure and Geographic Information Systems to integrate the components. This allowed for risk zoning in three levels at the census block level. The methodology aligns with the new guidelines from the Ministry of Housing and Urbanism, which introduce standards for quantifying risk in the TPIs through integrated matrices based on levels of hazard and vulnerability. The results show that 16,433 inhabitants are exposed to tsunami risk in the province, of which 46% face high risk, with the commune of Cartagena standing out (having the highest number of census blocks and population with high vulnerability and risk). This approach represents a key opportunity to reduce exposure and vulnerability in the province, establishing a replicable model for other coastal areas.

The “El Niño” phenomenon periodically affects the Piura region in Peru, causing heavy rains that increase the flow of the Piura River and, in some cases, lead to overflows, as occurred in 2017. This event poses a latent risk to the inhabitants of the districts of Piura, Castilla, Catacaos, and Cura Mori. The objective of this study was to estimate the surface flow time and velocity in four segments of the Piura River. To achieve this, the float method was used, which consisted of measuring the time it takes for a floating object to move between established points. Measurements were taken at the Andrés Avelino Cáceres, Eguiguren, Sánchez Cerro, San Miguel, and Bolognesi bridges. The experimentation was limited to low-magnitude flow rates, in accordance with the hydrometeorological conditions present during the months of March in 2019 and 2021, which gives the results an estimated character. The findings indicate that as the flow rate (m³/s) increases, the travel time of the water masses decreases, and the surface velocity increases proportionally. For example, a flow rate of 422 m³/s was associated with a velocity of 1.14 m/s, meaning that the water takes approximately 28 minutes to travel across the four evaluated segments.

In risk management processes, it is crucial to incorporate the knowledge, perceptions, and needs of civil society to develop effective disaster prevention, mitigation, and response strategies that reduce vulnerability in territories. To achieve this, methodological approaches in research-intervention must enable active community involvement, acknowledge multiple contextual realities, and generate a wealth of information that provides a sincere and consensus-based understanding of the reality being addressed. The objective of this article is to present a methodological proposal for data collection to strengthen risk management in communities, and evidence of its usefulness in this area of research. Video-walks, social mapping, and community workshops are proposed as key strategies to promote constructive dialogue among all stakeholders and facilitate collaborative action in disaster risk management.

In recent decades, changes in climate have intensified meteorological phenomena, such as strong waves. In the Central Pacific region of Costa Rica, the communities of Caldera and La Cueva have been severely affected by these events. To analyze vulnerability and threat perception, surveys were conducted in 23 homes in both communities. The proximity of homes to the coast and their retreat, as well as the low economic condition and lack of social organization, result in an increase in physical and socioeconomic vulnerability. 52.1% of the surveys reveal that climate change and the construction of the Caldera port are perceived as the main causes of coastal erosion. As part of proposals, rigid structural measures such as breakwaters and dikes turn out to be the most mentioned by locals (56.5%). Both communities have high exposure to extreme events and difficulties recovering, with the need to involve community participation in risk management.