Search Results (268)

This article investigates the macroeconomic and labor market conditions that shape the adoption of artificial intelligence (AI) technologies among large firms in Europe. Based on panel data econometrics and supervised machine learning techniques, we estimate how public health spending, access to credit, export activity, gross capital formation, inflation, openness to trade, and labor market structure influence the share of firms that adopt at least one AI technology. The research covers all 28 EU members between 2018 and 2023. We employ a set of robustness checks using a combination of fixed-effects, random-effects, and dynamic panel data specifications supported by Clustering and supervised learning techniques. We find that AI adoption is linked to higher GDP per capita, healthcare spending, inflation, and openness to trade but lower levels of credit, exports, and capital formation. Labor markets with higher proportions of salaried work, service occupations, and self-employment are linked to AI diffusion, while unemployment and vulnerable work are detractors. Cluster analysis identifies groups of EU members with similar adoption patterns that are usually underpinned by stronger economic and institutional fundamentals. The results collectively suggest that AI diffusion is shaped not only by technological preparedness and capabilities to invest but by inclusive macroeconomic conditions and equitable labor institutions. Targeted policy measures can accelerate the equitable adoption of AI technologies within the European industrial economy. Full article

Accurate diagnosis of gastrointestinal (GI) diseases typically requires invasive procedures or imaging studies that pose the risk of various post-procedural complications or involve radiation exposure. Bowel sounds (BSs), though typically described during a GI-focused physical exam, are highly inaccurate and variable, with low clinical value in diagnosis. Interpretation of the acoustic characteristics of BSs, i.e., using a phonoenterogram (PEG), may aid in diagnosing various GI conditions non-invasively. Use of artificial intelligence (AI) and improvements in computational analysis can enhance the use of PEGs in different GI diseases and lead to a non-invasive, cost-effective diagnostic modality that has not been explored before. The purpose of this work was to develop an automated AI model, You Only Listen Once (YOLO), to detect prominent bowel sounds that can enable real-time analysis for future GI disease detection and diagnosis. A total of 110 2-minute PEGs sampled at 44.1 kHz were recorded using the Eko DUO^® stethoscope from eight healthy volunteers at two locations, namely, left upper quadrant (LUQ) and right lower quadrant (RLQ) after IRB approval. The datasets were annotated by trained physicians, categorizing BSs as prominent or obscure using version 1.7 of Label Studio Software^®. Each BS recording was split up into 375 ms segments with 200 ms overlap for real-time BS detection. Each segment was binned based on whether it contained a prominent BS, resulting in a dataset of 36,149 non-prominent segments and 6435 prominent segments. Our dataset was divided into training, validation, and test sets (60/20/20% split). A 1D-CNN augmented transformer was trained to classify these segments via the input of Mel-frequency cepstral coefficients. The developed AI model achieved area under the receiver operating curve (ROC) of 0.92, accuracy of 86.6%, precision of 86.85%, and recall of 86.08%. This shows that the 1D-CNN augmented transformer with Mel-frequency cepstral coefficients achieved creditable performance metrics, signifying the YOLO model’s capability to classify prominent bowel sounds that can be further analyzed for various GI diseases. This proof-of-concept study in healthy volunteers demonstrates that automated BS detection can pave the way for developing more intuitive and efficient AI-PEG devices that can be trained and utilized to diagnose various GI conditions. To ensure the robustness and generalizability of these findings, further investigations encompassing a broader cohort, inclusive of both healthy and disease states are needed. Full article

The relationships between farmers and livestock are multifaceted. The aim of this study was to describe the sociodemographic, biogeographic, and institutional factors that influence the relationships between humans and animals in the natural savanna. Visits were made to 65 farms, followed by interviews (n = 13) and three focus group interviews (n = 24) directed at farmers and institutional representatives. The results were triangulated to extract the key findings. The following findings were obtained: (a) cultural gender transitions and the lack of generational succession have transformed livestock farming; (b) the relationships between farmers and livestock have favored the implementation of new productive practices and innovations, as well as improvements in animal welfare practices; (c) conditioning factors affecting these relationships include gender discriminatory norms, low profitability and credit access, poor sanitation, animal handling infrastructure, security, and resistance to change; and (d) improvement opportunities include the inclusion of young people and women in livestock farming, education for work practices, credit facilitation, access to technologies, governance, and improvement in the cattle logistics chain. The results are useful for enhancing the relationships between farmers and livestock, guiding training activities, and responsible governance. Full article

Restrictive conditions that financial institutions require on credit allocation remain the main constraints to developing and creating new businesses. In this context, the concept of private equity came to fill this problem. However, because it is a riskier business, investors thoroughly assess before investing in a firm’s capital. This work aims to analyze the criteria of private equity investment and explore how Tunisian private equity investors make investment decisions. The methodology applied aligns with prior works studying investment criteria used by private equity investors. Results show that 100% of investors prefer to invest in firms that aim to achieve some growth and are in the development phase. In addition, under informational asymmetry between entrepreneurs and investors, the latter place greater importance on the business plan, information gathered during interviews with promoters, and information on the products. Full article

Accurate corporate credit ratings are essential for financial risk assessment; yet, traditional methodologies relying on manual evaluation and basic statistical models often fall short in dynamic economic conditions. This study investigated the potential of machine-learning (ML) algorithms as a more precise and adaptable alternative for credit rating predictions. Using a seven-year dataset from S&P Capital IQ Pro, corporate credit ratings across 20 countries were analyzed, leveraging 51 financial and business risk variables. The study evaluated multiple ML models, including Logistic Regression, Support Vector Machines, Decision Trees, Random Forest, Gradient Boosting (GB), and Neural Networks, using rigorous data pre-processing, feature selection, and validation techniques. Results indicate that Artificial Neural Networks (ANN) and GB consistently outperform traditional models, particularly in capturing non-linear relationships and complex interactions among predictive factors. This study advances financial risk management by demonstrating the efficacy of ML-driven credit rating systems, offering a more accurate, efficient, and scalable solution. Additionally, it provides practical insights for financial institutions aiming to enhance their risk assessment frameworks. Future research should explore alternative data sources, real-time analytics, and model explainability to facilitate regulatory adoption. Full article

This study focuses on the shift to a circular economy (CE) in the textile, apparel, and fashion (TAF) sectors, which generate tons of waste annually. Thus, embracing CE practices is essential for contributing to UN Sustainable Development Goals. This study employs a mixed-methods approach, integrating PRISMA for systematic literature selection, BERTopic modeling and AI-driven SDG mapping, and case study analysis to explore emerging CE themes, implemented circular practices, and systemic barriers. Machine-learning-based SDG mapping reveals strong linkages to SDG 9 and SDG 12, emphasizing technological advancements, industrial collaborations, and circular business models. Moderately explored SDGs, namely, SDG 8, SDG 6, and SDG 7, highlight research on labor conditions, water conservation, and clean energy integration. Reviewing 655 peer-reviewed papers, the BERTopic modeling extracted six key themes, including sustainable recycling, circular business models, and consumer engagement, whereas case studies highlighted regulatory frameworks, stakeholder collaboration, and financial incentives as critical enablers. The findings advance institutional theory by demonstrating how certifications, material standards, and regulations drive CE adoption, reinforcing SDG 12 and SDG 16. The natural resource-based view is extended by showing that technological resources alone are insufficiently aligned with SDG 9. Using the Antecedents–Decisions–Outcomes framework, this study presents a structured, AI-driven roadmap for scaling CE in the TAF industry, addressing systemic barriers, and supporting global sustainability goals, highlighting how multistakeholder collaboration, digital traceability, and inclusive governance can improve the impact of CE. The results recommend that CE strategies should be aligned with net-zero targets, carbon credit systems, and block-chain-based supply chains. Full article

Climate variability intensifies weather risks across smallholder rainfed farming systems in Africa. Farmers often respond by minimizing the use of modern inputs and opting for low-cost traditional practices, a strategy that decreases average yields and perpetuates poverty. While crop insurance could incentivize greater adoption of inputs, indemnity-based programs face market failures. Weather index insurance (WII), which utilizes objective weather data to trigger payouts while addressing traditional crop insurance market failures, is a viable solution. However, empirical evidence on the impact of WII remains limited, with most studies relying on controlled experiments or hypothetical scenarios that overlook real-world adoption dynamics. This study analyzed observational data from 400 smallholder farmers across diverse agroecological zones in Njoro Sub-County, Kenya, using instrumental variable regression to evaluate the impact of weather index insurance (WII) on input adoption and intensity of use. Findings indicated that WII significantly increased the adoption and intensification of improved inputs while displacing traditional practices, with effects moderated by gender, financial access, and infrastructure. Specifically, active WII users applied 28.7 kg/acre more chemical fertilizer and used 2.6 kg/acre more hybrid maize seeds while reducing manure and traditional seed usage by 27 kg/acre and 2.9 kg/acre, respectively. However, the effectiveness of WII was context-dependent, varying under extreme drought conditions and in high-fertility soils, which directly affected resilience outcomes. These findings suggest that policies should combine insurance with targeted agroecological practices and complementary measures, such as improved access to credit and gender-sensitive extension programs tailored to the specific needs of women farmers, to support sustainable agricultural transformation. Full article

This study introduces a novel approach for analyzing the dynamic interplay among key economic indicators by employing a Caputo Fractional Fisher Information framework combined with partial information decomposition. By integrating fractional derivatives into traditional Fisher Information metrics, our methodology captures long-range memory effects that govern the evolution of monetary policy, credit risk, market volatility, and inflation, represented by INTEREST, CDS, VIX, CPI, and PPI, respectively. We perform a comprehensive comparative analysis using rolling-window estimates to generate Caputo Fractional Fisher Information values at different fractional orders alongside the memoryless Ordinary Fisher Information. Subsequent correlation, cross-correlation, and transfer entropy analyses reveal how historical dependencies influence both unique and synergistic information flows between indices. Notably, our partial information decomposition results demonstrate that deep historical interactions significantly amplify the informational contribution of each indicator, particularly under long-memory conditions, while the Ordinary Fisher Information framework tends to underestimate these synergistic effects. The findings underscore the importance of incorporating memory effects into information-theoretic models to better understand the intricate, time-dependent relationships among financial indicators, with significant implications for forecasting and policy analysis. Full article

Challenges in implementing machine learning (ML) include expanding data resources within the finance sector. Banking data with significant financial implications are highly confidential. Diverse breaches and privacy violations can result from a combination of user information from different institutions for banking purposes. To address these issues, federated learning (FL) using a flower framework is utilized to protect the privacy of individual organizations while still collaborating through separate models to create a unified global model. However, joint training on datasets with diverse distributions can lead to suboptimal learning and additional privacy concerns. To mitigate this, solutions using federated averaging (FedAvg), federated proximal (FedProx), and federated optimization methods have been proposed. These methods work with data locality during training at local clients without exposing data, while maintaining global convergence to enhance the privacy of local models within the framework. In this analysis, the UNSW-NB15 and credit datasets were employed, utilizing precision, recall, accuracy, F1-score, ROC, and AUC as performance indicators to demonstrate the effectiveness of the proposed strategy using FedAvg, FedProx, and FedOpt. The proposed algorithms were subjected to an empirical study, which revealed significant performance benefits when using the flower framework. Consequently experiments were conducted over 50 rounds using the UNSW-NB15 dataset, which achieved accuracies of 99.87% for both FedAvg and FedProx and 99.94% for FedOpt. Similarly, with the credit dataset under the same conditions, FedAvg and FedProx achieved accuracies of 99.95% and 99.94%, respectively. These results indicate that the proposed framework is highly effective and can be applied in real-world applications across various domains for secure and privacy-preserving collaborative machine learning. Full article

This study examines whether the gaps in four financial well-being (FWB) indicators—emergency fund availability, spending less than income, perceived financial comfort, and no credit card debt—between groups with varying levels of financial literacy changed during the economic disruptions of 2020–2022 compared to the more stable period of 2017–2019. Using data from the 2017–2022 waves of the Survey of Household Economics and Decisionmaking conducted by the Federal Reserve Board, this study applies difference-in-differences and event study methods to explore these trends. Descriptive findings, consistent with prior research, show that respondents with higher financial literacy reported greater FWB across all years. Regression estimates based on respondents who provided definitive answers (correct or incorrect) to the Big Three financial literacy questions suggest that the pre-existing gaps in emergency fund availability and perceived financial comfort between respondents with higher and lower financial literacy widened in 2020–2022, whereas the gap in spending less than income remained unchanged. There is some evidence of a widening gap in the likelihood of having no credit card debt, but the estimates are less conclusive. In general, these results indicate that higher financial literacy might have served as a protective factor for some aspects of FWB amid the challenging economic conditions of 2020–2022. However, results based on respondents who provided either correct or “don’t know” answers to the same questions differ in direction from the results of the earlier analysis. The findings of this study have implications for measuring financial literacy and investigating its role in shaping FWB. Full article

Robust credit risk prediction in emerging economies increasingly demands the integration of external factors (EFs) beyond borrowers’ control. This study introduces a scenario-based methodology to incorporate EF—namely COVID-19 severity (mortality and confirmed cases), climate anomalies (temperature deviations, weather-induced road blockages), and social unrest—into machine learning (ML) models for credit delinquency prediction. The approach is grounded in a CRISP-DM framework, combining stationarity testing (Dickey–Fuller), causality analysis (Granger), and post hoc explainability (SHAP, LIME), along with performance evaluation via AUC, ACC, KS, and F1 metrics. The empirical analysis uses nearly 8.2 million records compiled from multiple sources, including 367,000 credit operations granted to individuals and microbusiness owners by a regulated Peruvian financial institution (FMOD) between January 2020 and September 2023. These data also include time series of delinquency by economic activity, external factor indicators (e.g., mortality, climate disruptions, and protest events), and their dynamic interactions assessed through Granger causality to evaluate both the intensity and propagation of external shocks. The results confirm that EF inclusion significantly enhances model performance and robustness. Time-lagged mortality (COVID MOV) emerges as the most powerful single predictor of delinquency, while compound crises (climate and unrest) further intensify default risk—particularly in portfolios without public support. Among the evaluated models, CNN and XGB consistently demonstrate superior adaptability, defined as their ability to maintain strong predictive performance across diverse stress scenarios—including pandemic, climate, and unrest contexts—and to dynamically adjust to varying input distributions and portfolio conditions. Post hoc analyses reveal that EF effects dynamically interact with borrower income, indebtedness, and behavioral traits. This study provides a scalable, explainable framework for integrating systemic shocks into credit risk modeling. The findings contribute to more informed, adaptive, and transparent lending decisions in volatile economic contexts, relevant to financial institutions, regulators, and risk practitioners in emerging markets. Full article

The aim of this study is to develop a convenient and effective entropy analysis method for assessing the efficiency of workload distribution among medical institution personnel. This research is based on a model for evaluating employee workload in conditional time units—credits—taking into account time-and-motion studies and the volume of medical services provided or tasks performed over a given period. The model and method developed by the authors enable the consideration of potential losses of working time and coefficients that determine the percentage of effective working time. The method is based on calculating and analyzing the values of normative and actual workloads of employees. The study introduces such indicators as relative workload, workload distribution entropy, and the entropy of free and excessively worked time credits. During the experimental verification of the developed method for analyzing the activities of a dental clinic, it was demonstrated that the method is both convenient and effective for analyzing the performance of individual employees as well as groups of employees. The results of the method are presented in a convenient and intuitively understandable form. Therefore, this method can serve as an effective tool for identifying internal reserves within the institution and making managerial decisions regarding its further operation. Full article

The Anthropocene has ushered in unprecedented environmental challenges, with invasive seaweed blooms emerging as a critical yet understudied facet of climate change. These blooms, driven by nutrient runoff and oceanic alterations, disrupt ecosystems, threaten biodiversity, and impose economic and public health burdens on coastal communities. However, invasive seaweeds also present an opportunity as a sustainable resource. This study explores the valorization of Sargassum spp. for agricultural applications, focusing on the development of biodegradable bioplastics and biostimulants. Field trials demonstrated the effectiveness of Marine Symbiotic^® Sargassum-derived biostimulant in distinct agricultural contexts. In the Dominican Republic, trials on pepper crops showed significant improvements, including a 33.26% increase in fruit weight, a 21.94% rise in fruit set percentage, a 45% higher yield under high-stress conditions, and a 48.42% reduction in fruit rejection compared to control. In Colombia, trials across four leafy green varieties revealed biomass increases of up to 360%, a 50% reduction in synthetic input dependency, and enhanced crop coloration, improving marketability. Additionally, Sargassum-based biofilms exhibited favorable mechanical properties and biodegradability, offering a sustainable alternative to conventional agricultural plastics. Carbon credit quantification revealed that valorizing Sargassum could prevent up to 89,670 tons of CO₂-equivalent emissions annually using just one Littoral Collection Module^® harvesting system, while biostimulant application enhanced carbon sequestration in crops. These findings underscore the potential of invasive seaweed valorization to address multiple climate challenges, from reducing plastic pollution and GHG emissions to enhancing agricultural resilience, thereby contributing to a sustainable Blue Economy and aligning with global sustainability goals. Full article

Sustainable development in educational environments requires a holistic approach to architectural design, balancing multiple environmental functions to optimize student well-being and energy efficiency. According to architectural standards, rectangular classrooms typically have a shallow proportion, meaning the external facade is longer than the internal sides. While this design ensures adequate natural lighting, essential for classroom visual functions, it may not fully align with the sustainability goals in regions with diverse environmental characteristics. This diversity can lead to shortcomings in other aspects of human comfort or environmental performance, as optimizing one function may negatively impact others, while the environmental efficiency of architectural spaces should not be judged solely on a single comfort criterion. A holistic study should evaluate common architectural shapes and proportions to ensure they align with the Green Architectural principles for specific locations. This manuscript compares eight rectangular classrooms with different external-to-internal wall proportions and window-to-wall ratios (WWR) to determine their suitability for Taif City, KSA schools. The case studies include variations in window sizes (10.5 m² and 14 m²) and orientations (North and South), providing a comprehensive evaluation of their impact on human comfort. Simulation results reveal that the common classroom proportion did not yield the highest green credits, suggesting it may not be optimal for all regions, including Taif City. The findings emphasize the need to reconsider standard classroom dimensions to better align with local environmental conditions and Green Architecture principles, contributing to the broader goals of sustainability and sustainable development in educational infrastructure. Full article

Forecast risk management is central to the financial management process. This study aims to apply Monte Carlo simulation to solve three classic probabilistic paradoxes and discuss their implementation in corporate financial management. The article presents Monte Carlo simulation as an advanced tool for risk management in financial management processes. This method allows for a comprehensive risk analysis of financial forecasts, making it possible to assess potential errors in cash flow forecasts and predict the value of corporate treasury growth under various future scenarios. In the investment decision-making process, Monte Carlo simulation supports the evaluation of the effectiveness of financial projects by calculating the expected net value and identifying the risks associated with investments, allowing more informed decisions to be made in project implementation. The method is used in reducing cash flow volatility, which contributes to lowering the cost of capital and increasing the value of a company. Simulation also enables more accurate liquidity planning, including forecasting cash availability and determining appropriate financial reserves based on probability distributions. Monte Carlo also supports the management of credit and interest rate risk, enabling the simulation of the impact of various economic scenarios on a company’s financial obligations. In the context of strategic planning, the method is an extension of decision tree analysis, where subsequent decisions are made based on the results of earlier ones. Creating probabilistic models based on Monte Carlo simulations makes it possible to take into account random variables and their impact on key financial management indicators, such as free cash flow (FCF). Compared to traditional methods, Monte Carlo simulation offers a more detailed and precise approach to risk analysis and decision-making, providing companies with vital information for financial management under uncertainty. This article emphasizes that the use of Monte Carlo simulation in financial management not only enhances the effectiveness of risk management, but also supports the long-term growth of corporate value. The entire process of financial management is able to move into the future based on predicting future free cash flows discounted at the cost of capital. We used both numerical and analytical methods to solve veridical paradoxes. Veridical paradoxes are a type of paradox in which the result of the analysis is counterintuitive, but turns out to be true after careful examination. This means that although the initial reasoning may lead to a wrong conclusion, a correct mathematical or logical analysis confirms the correctness of the results. An example is Monty Hall’s problem, where the intuitive answer suggests an equal probability of success, while probabilistic analysis shows that changing the decision increases the chances of winning. We used Monte Carlo simulation as the numerical method. The following analytical methods were used: conditional probability, Bayes’ rule and Bayes’ rule with multiple conditions. We solved truth-type paradoxes and discovered why the Monty Hall problem was so widely discussed in the 1990s. We differentiated Monty Hall problems using different numbers of doors and prizes. Full article