Risk Framework Research Articles

Empirical and Machine Learning Models for Soil Erosion Risk Assessment: A Case Study of Tsageri Municipality, Georgia

Soil erosion caused by water is one of the most common causes of land degradation worldwide. Within framework of this research soil erosion risk in Tsageri municipality, Georgia was evaluated using Revised Universal Soil Loss Equation (RUSLE) and a machine learning-based Random Forest (RF) model. Open access digital datasets and field observations collected in 2023-2024, which included visually identified erosion areas and GPS-recorded data on the presence or absence of erosion, were utilized in modeling process. Data processing and modeling conducted using ArcGIS Pro 3.0 and RStudio software. According to RUSLE results, 39.7% of the study area falls under the very low erosion risk zone, and 20.7% is in the very high risk zone. The RF model results indicated that 16.5% of the territory is under very low risk of erosion and 13.9% - very high risk. It was observed that RUSLE model tends to overestimate erosion rates on steep, forested slopes, while the RF model, by incorporating additional variables, provided more accurate prediction. These findings suggest that combining RUSLE with machine learning improves soil erosion risk assessment, particularly in complex landscapes such as in Tsageri municipality. Future researche should focus on testing additional variables to refine the modeling process further and enhance predictions. The generated digital thematic maps offer valuable insights for understanding the spatial dynamics of soil erosion within the study area, analyzing the factors driving the process and developing effective mitigation strategies.

Evaluating the Impact of Technological Innovations on Operational Risk Management in Financial Institutions

This study evaluates the impact of technological innovations on operational risk management in financial institutions, focusing on how emerging technologies influence risk identification, mitigation, and management processes. Employing a qualitative approach through literature review and library research, this study synthesizes recent findings on the integration of technologies such as artificial intelligence (AI), blockchain, big data analytics, and cloud computing within financial risk frameworks. Findings indicate that these technologies offer substantial improvements in risk management by enhancing accuracy in risk detection, increasing response speed, and reducing human error. AI and machine learning models, for instance, are shown to enable real-time monitoring and predictive analytics, allowing institutions to identify potential risks before they materialize. Blockchain technology improves transparency and security in transaction processing, thereby mitigating fraud-related risks. Big data analytics provides insights into customer behavior, which can help detect anomalous activities and improve decision-making. However, the study also highlights challenges, including the need for robust cybersecurity measures, potential regulatory gaps, and skill shortages in handling complex technological systems. This study provides insights for financial institutions aiming to balance technological integration with effective risk management, underscoring the need for comprehensive frameworks that align technological advancements with regulatory compliance and organizational capability. Future research should focus on empirical studies assessing the long-term implications of these technologies on risk management efficacy in diverse financial settings.

Understanding users’ news-sharing behaviors: roles of risk perception, believability, fake news awareness and social tie variety

PurposeThis study aims to investigate the impact of news quality on users’ risk perceptions toward online news and its subsequent influence on perceived believability and user engagement in sharing news. Additionally, we explore the moderating effects of fake news awareness and social tie variety.Design/methodology/approachDrawing upon the social amplification of risk framework, this study investigates the relationship between news quality and users’ news-sharing behaviors, along with its underlying mechanism. An online questionnaire involving 399 eligible participants was employed for hypotheses testing, and the structural equation model served as the main analytical method.FindingsThe influence of news quality on users’ news-sharing behavior is sequentially mediated by risk perception and perceived believability. Individuals with a heightened awareness of fake news or a diverse social tie are more inclined to perceive greater risks associated with news-sharing behavior and question news authenticity.Originality/valueThis study contributes to the existing literature on users’ news-sharing behaviors by examining the influence of risk perception on the relationship between news quality, perceived believability and users’ news-sharing behavior. Additionally, it explores the moderating effects of fake news awareness and social tie variety. Our findings offer valuable insights into comprehending user inclinations towards news sharing and mitigating the dissemination of fake news.

Long-Term Ozone Exposure, COPD, and Asthma Mortality: A Retrospective Cohort Study in the Republic of Korea

Ozone concentrations have increased in recent decades, and several studies have reported that long-term exposure to ozone increases the mortality risk induced by respiratory conditions. However, research on cause-specific mortality related to ozone exposure and respiratory diseases remains scarce. We constructed a retrospective cohort of 5,360,032 adults aged ≥ 65 years from the National Health Insurance Service of Republic of Korea, and death certificates were obtained from Statistics Republic of Korea to determine the cause of death between 2010 and 2019. The daily maximum 8 h average levels of ozone during the warm season annually (May–September) and other air pollutants were determined for the residential district. We analyzed the data using a time-varying Cox proportional hazards model with individual- and district-level covariates, incorporating a competing risk framework to address deaths from causes other than chronic obstructive pulmonary disease (COPD) and asthma. In our single-pollutant model with a 3-year moving average, a 1 ppb increase in ozone exposure was associated with a hazard ratio (HR) of 1.011 (95% confidence interval [CI]: 1.008–1.013) for COPD mortality and an HR of 1.016 (95% CI: 1.011–1.022) for asthma mortality. In our model adjusted for the presence of underlying diseases and district-level variables, the HRs were 1.009 (95% CI: 1.008–1.014) for COPD and 1.017 (95% CI: 1.011–1.023) for asthma, respectively. These associations remained robust in our two-pollutant model, except for NO2 and COPD. A linear concentration–response relationship was identified between ozone concentration, COPD, and asthma mortality. In this large nationwide cohort study, long-term exposure to ozone was associated with an increased risk of death from COPD and asthma in older Korean adults.

Development and validation of a risk predictive nomogram for colon cancer-specific mortality: a competing risk model based on the SEER database

BackgroundUtilizing the SEER database, we developed a competing risk model along with a nomogram designed for the early identification of colon cancer-specific mortality (CSM) risk.MethodsClinical and pathological information, along with other significant data, were obtained from the SEER database. Patients were randomly divided into a training set and a validation set. We investigated the independent factors affecting CSM among colon cancer patients using univariate and multivariate analyses within a competing risk framework, ultimately developing a predictive tool for CSM in colon cancer.ResultsInvolving 40,261 individuals diagnosed with colon cancer, our study included 10,397 deaths directly due to the disease and an additional 5,828 from other causes. We used a competing risk model to predict cancer-specific mortality (CSM) in these patients. For the training dataset, the model’s area under the curve (AUC) for predicting 1-, 3-, and 5-year cancer-specific survival (CSS) was 0.835 (95% confidence interval [CI] 0.826 to 0.844), 0.849 (95% CI 0.843 to 0.855), and 0.843 (95% CI 0.836 to 0.850), respectively. In the validation group, the AUC values for the same time periods were 0.846 (95% CI 0.833 to 0.860), 0.853 (95% CI 0.843 to 0.862), and 0.846 (95% CI 0.835 to 0.856), respectively. In comparison, traditional survival analysis yielded higher cumulative CSM rates over time than those provided by our competing risk approach.ConclusionWe created a competitive risk assessment model along with a predictive tool designed to estimate CSM in patients with colon cancer. This nomogram demonstrates high accuracy and reliability, aiding medical professionals in making clinical decisions and developing patient follow-up plans.

Effects of Phenology on Plant Community Assembly and Structure

Phenology—the timing of critical stages of growth and reproduction and the transitions between them—determines environmental conditions and biotic interactions. Hence, phenology is a key functional trait influencing organisms’ survival and fitness; however, the role of phenology in community assembly processes has been less considered. Here we review the importance of phenology in environmental and biotic filtering, structuring priority effects, and species coexistence in the context of the assembly of native communities, as well as in invasions and restoration. We highlight the complexity of the life-history aspect of phenology, which makes simple trade-offs—such as between growth timing and competitive ability—part of larger plant strategies shaped by a framework of risk, reward, and investment over multiple timescales. Embracing this complexity could yield insights into how phenology shapes communities.

Safety of hepatitis E vaccine in pregnancy: an emulated target trial following a mass reactive vaccination campaign in Bentiu internally displaced persons camp, South Sudan

Epidemic forms of hepatitis E cause high mortality among pregnant people, with case fatality risks over 30% and adverse fetal outcomes. In 2022, the first mass reactive vaccination campaign against hepatitis E was conducted in South Sudan with the HEV239 vaccine. We aimed to assess whether vaccination against hepatitis E in pregnancy increases the risk of fetal loss in a cohort of vaccinated and unvaccinated pregnant people. In this emulated target trial, an exhaustive pregnancy census was conducted in Bentiu internally displaced persons camp after the second of three vaccination rounds. Women and girls aged 14-45 years with no current jaundice or acute illness were eligible for participation. Individuals who consented were revisited 28 days after their delivery date to document the pregnancy outcome. We used an emulated target trial framework to address biases inherent in observational studies. We matched vaccinated to unvaccinated participants on age, gestational age, and vaccination propensity score and estimated cumulative incidence functions for fetal loss in vaccinated compared to unvaccinated women in a competing risks framework using the Aalen-Johansen estimator. Between May 16 and June 30, 2022, 3421 participants were enrolled and followed up for inclusion in analysis. Among 2741 women who had a pregnancy outcome after the start of the vaccination campaign, 67 (2·4%) were vaccinated before conception, 2036 (74·3%) were vaccinated during pregnancy, and 638 (23·2%) were not vaccinated. Among the 2407 women retained in the matched analyses, the cumulative risk of fetal loss among individuals vaccinated during pregnancy was 7·2% (95% CI 5·6-8·7) compared with 6·1% (3·7-9·2) among unvaccinated individuals, implying a risk ratio of 1·2 (95% CI 0·7-1·9). No evidence of increased risk of fetal loss was found among individuals vaccinated during pregnancy. Médecins Sans Frontières.

A fire risk pre-warning framework for high-rise buildings based on unascertained method

The growing global interest in preventing and controlling fires in high-rise buildings reflects the increasing significance of this issue today. This research aims to establish an early warning framework for fire risk in high-rise buildings. Firstly, considering the importance of a scientific indicator system for the application of the model, this study combines the event analysis method with the building design fire code to identify 11 key risk factors that have a far-reaching impact on the prevention of fires in high-rise buildings. Based on identifying the risk factors, a high-rise building fire risk warning tree is also established, which scientifically solves the problem of the indicator system of the warning object. Subsequently, in response to the various complex issues arising from the uncertainty of fire occurrence in high-rise buildings, this study adopts the unascertained method to model the fire risk of high-rise buildings for early warning. In addition, the developed methodology was empirically validated through case studies and analyses of empirical data on fire risks in nine representative high-rise buildings. The results of the unascertained method were also compared with the results of the K-means method, from which it was concluded that the unascertained method can predict building fires more accurately. The research results provide a reliable decision support system for fire disaster prevention and control in high-rise buildings.

Extracorporeal Membrane Oxygenation for COVID-19 During the Delta and Omicron Waves in North America.

Clinical outcomes for patients with severe acute respiratory failure caused by different variants of the coronavirus disease 2019 (COVID-19) supported with extracorporeal membrane oxygenation (ECMO) are incompletely understood. Clinical characteristics, pre-ECMO management, and hospital mortality at 90 days for adults with COVID-19 who received venovenous ECMO (VV-ECMO) at North American centers during waves predominated by Delta (August 16 to December 12, 2021) and Omicron (January 31 to May 31, 2022) severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) variants were compared in a competing risks framework. One thousand seven hundred and sixty-six patients (1,580 Delta, 186 Omicron) received VV-ECMO for COVID-19 during the Delta- and Omicron-predominant waves in North American centers. In the unadjusted competing risks model, no significant difference was observed in risk of hospital mortality at 90 days between patients during the Delta- versus Omicron-predominant wave (subhazard ratio [sHR], 0.94; 95% confidence interval [CI], 0.74-1.19), but patients supported with VV-ECMO during the Omicron-predominant wave had a significantly lower adjusted risk of hospital mortality at 90 days (subhazard ratio, 0.71; 95% CI, 0.51-0.99). Patients receiving VV-ECMO during the Omicron-predominant wave had a similar unadjusted risk of hospital mortality at 90 days, but a significantly lower adjusted risk of hospital mortality at 90 days than those receiving VV-ECMO during the Delta-predominant wave.

Re‐hearing parents as risks to children: Institutional listening practices in a California child welfare court

AbstractBuilding on scholarship on the politics of listening and the listening subject, this article proposes re‐hearing as a listening practice where empowered actors assert that various qualities of personhood are hearable or perceivable in relation to what marginalized persons say, do, or are otherwise associated with. Although there is an expectation that in US courts lay actors can have a hearing and a voice before the law, I identify how practices of re‐hearing shaped how parents and their narratives were heard (or left unheard) in a California child welfare court. My ethnographic research examined the listening and entextualization practices of judges, attorneys, and social workers involved in child welfare case management in California. I found that re‐hearing practices co‐constructed the continued marginalization of lay actors within contexts of state surveillance by attributing suspicion to parents and their silences in ways that exceeded and constructed evidence collected against them. Ultimately, I argue that child welfare courts and professional actors within them collectively comprise a listening institution that normalizes re‐hearing low‐income and racialized parents through frameworks of deficiency and risk.

A Framework for Construction-related Risks by integrating the Fuzzy Grey Comprehensive Evaluation Method (FGCE)

There are five basic phases for construction projects: planning, design, tendering, construction and maintenance. The risks of each phase have an impact on time, cost, and quality. In this paper, the tendering phase of the residential complex project was investigated as a case study, and the creation of a fuzzy and grey correlation analysis model was examined using a fuzzy theory and a grey correlation theory to dispel the professional judgment around the project phase. Creating a comparison and a reference matrix based on grey theory and/by examining factors and their impact on duration, cost, and quality separately, gives the construction investors a scientific, direct, flexible, and adaptable technique to assess project risks. The described method categorized the tendering phase risk based on the three project determinants: duration, cost, and quality. The correlation degree is greater than 0.5, hence construction project duration risk is almost nonexistent. The project investor must also investigate risk assumption, reduction, diversion, and evasion tactics to handle cost and quality risks, which are between 0.2 and 0.5. This suggests that tender phase issues do not affect project length but do affect cost and quality, requiring attention and action.

Analysis of the List of Risks Affecting the Verification of Measuring Instruments

The purpose of this study is to identify and analyze the risks accompanying the process of verification of measuring instruments in metrological services. Risks are analyzed within the framework of a holistic risk and opportunity management system aimed at identifying and managing potential threats and opportunities affecting the achievement of the ultimate goals of the organization. Risk is defined as a possible negative event that could affect project performance and is evaluated by probability of occurrence and possible consequences. The objectives of risk and opportunity management are aimed at ensuring the achievement of the capabilities of the metrology service under conditions of uncertainty. Effective risk assessment of the process of verification of measuring instruments requires a comprehensive approach. In this regard, in the course of the study the regulatory framework was considered, regulating activities in the field of ensuring the uniformity of measurements, identified internal and external environmental factors affecting the process of verification of measuring instruments, identified stakeholders in the field of metrology services. Procedures for risk identification, analysis, assessment and management have been developed within the system. The list of typical risks and opportunities in the process of verification of measuring instruments in the relationship with environmental factors and possible consequences for the organization is compiled. The developed list of potential risks and opportunities is typical for the process of verification of measuring instruments and therefore can be recommended to employees of metrological services of enterprises. With its help it is possible to assess in advance the potential risks and opportunities in the metrological field and to achieve a more effective result by minimizing the negative consequences.

Minimum capital requirement portfolios according to the new Basel framework for market risk

Minimum capital requirement portfolios according to the new Basel framework for market risk

Integrating traditional and non-traditional model risk frameworks in credit scoring

Background: An improved understanding of the reasoning behind model decisions can enhance the use of machine learning (ML) models in credit scoring. Although ML models are widely regarded as highly accurate, the use of these models in settings that require explanation of model decisions has been limited because of the lack of transparency. Especially in the banking sector, model risk frameworks frequently require a significant level of model interpretability.Aim: The aim of the article is to evaluate traditional model risk frameworks to determine their appropriateness when validating ML models in credit scoring and enhance the use of ML models in regulated environments by introducing a ML interpretability technique in model validation frameworks.Setting: The research considers model risk frameworks and regulatory guidelines from various international institutions.Method: The research is qualitative in nature and shows how through integrating traditional and non-traditional model risk frameworks, the practitioner can leverage trusted techniques and extend traditional frameworks to address key principles such as transparency.Results: The article proposes a model risk framework that utilises Shapley values to improve the explainability of ML models in credit scoring. Practical validation tests are proposed to enable transparency of model input variables in the validation process of ML models.Conclusion: Our results show that one can formulate a comprehensive validation process by integrating traditional and non-traditional frameworks.Contribution: This study contributes to existing model risk literature by proposing a new model validation framework that utilises Shapley values to explain ML model predictions in credit scoring.

Sudden cardiac death after myocardial infarction: individual participant data from pooled cohorts.

Risk stratification of sudden cardiac death after myocardial infarction and prevention by defibrillator rely on left ventricular ejection fraction (LVEF). Improved risk stratification across the whole LVEF range is required for decision-making on defibrillator implantation. The analysis pooled 20 data sets with 140 204 post-myocardial infarction patients containing information on demographics, medical history, clinical characteristics, biomarkers, electrocardiography, echocardiography, and cardiac magnetic resonance imaging. Separate analyses were performed in patients (i) carrying a primary prevention cardioverter-defibrillator with LVEF ≤ 35% [implantable cardioverter-defibrillator (ICD) patients], (ii) without cardioverter-defibrillator with LVEF ≤ 35% (non-ICD patients ≤ 35%), and (iii) without cardioverter-defibrillator with LVEF > 35% (non-ICD patients >35%). Primary outcome was sudden cardiac death or, in defibrillator carriers, appropriate defibrillator therapy. Using a competing risk framework and systematic internal-external cross-validation, a model using LVEF only, a multivariable flexible parametric survival model, and a multivariable random forest survival model were developed and externally validated. Predictive performance was assessed by random effect meta-analysis. There were 1326 primary outcomes in 7543 ICD patients, 1193 in 25 058 non-ICD patients ≤35%, and 1567 in 107 603 non-ICD patients >35% during mean follow-up of 30.0, 46.5, and 57.6 months, respectively. In these three subgroups, LVEF poorly predicted sudden cardiac death (c-statistics between 0.50 and 0.56). Considering additional parameters did not improve calibration and discrimination, and model generalizability was poor. More accurate risk stratification for sudden cardiac death and identification of low-risk individuals with severely reduced LVEF or of high-risk individuals with preserved LVEF was not feasible, neither using LVEF nor using other predictors.

The Social Contagion of Risk Perceptions of Emerging Technologies through Evolutionary Game in Networks

Emerging technologies are leading the fourth industrial revolution, bringing profound changes to modern life. However, the contagion of public risk perceptions pertaining to these technologies may result in new social stability risks according to the social amplification of risk framework (SARF). As such, understanding the formation and contagion mechanisms behind public risk perceptions of emerging technologies is critical to promoting their increased receptivity. Based on an evolutionary game theoretical approach to complex networks, this paper constructs a social contagion model of the risk perception of emerging technologies and uses simulations to analyze the influence of factors such as individual cognition and social environment. Results indicate the following: (1) the rate of risk perception contagion gradually increases with the level of individual risk perception and trust in communicators; (2) the risk perception contagion rate gradually decreases as the level of risk governance participation increases; and (3) comparing different social networks, kinship networks have a greater effect than social media networks on risk perception contagion.

Dynamic Analysis and Temporal Governance of Safety Risks: Evidence from Underground Construction Accident Reports

Due to the complexity and dynamics of underground construction projects, safety risk management has experienced significant challenges restricting the sustainable development of underground space. The research on risk causal chains and risk coupling has yet to reveal the dynamic interactive characteristics of these risk factors and their temporal relationships over time. This study utilized a complex system view for safety risk analysis, using 37 accident investigation reports of underground construction projects. Combined with two novel and emerging analytical methods, temporal qualitative comparative analysis and crisp-set qualitative comparative analysis, this study discusses the temporal relationship of risk factors to the cause of accidents and explores the multi-actor coupling characteristics of management risk. The findings indicate that (1) compared with general construction projects, underground construction should pay more attention to management safety risks because they have an obvious time lag effect expressed in all accident causation paths, namely, preceding management risk, management risk, and machine/material risk cross-concurrently, and management risk initiation and (2) underground construction project management risks have three key main paths, namely, single-actor-dominated management deficiency (supervisors, owners, and subcontractors that cause management risks as a single-core actor) and dual-actor-dominated management deficiency (owner and subcontractor as dual core actors of management risk). Multi-actor-dominated management deficiency (owners, subcontractors, and supervisors are the multiple core actors of management risk). This study thus developed a temporal governance framework of underground construction safety risks based on the synergy of multi-actors and proposed risk governance strategies, such as synergistic multi-actor governance, to consider the temporal relationship of safety risk. This study further reveals the temporal and coupling characteristics of safety risks to enrich the risk casual chain theory and risk coupling theory and establish a systematic risk analysis framework for new guidance for safety and risk management for underground construction projects.

Perceived risk, health protective behavior, and trust: a case study of the flint water crisis

ABSTRACT The Flint Water Crisis exemplifies one of the most significant environmental disasters in the recent U.S. history. While hazard exposure and effects pertaining to the crisis have been addressed, and technical experts have pronounced Flint’s water safe for consumption, media reports and stories from community members suggest that significant distrust remains among residents regarding their water supply. We use data from an online survey administered in Flint and surrounding counties in Southeast Michigan to examine the extent and variation in risk perception, health protective behavior, and trust in these communities with respect to their water supply. Conceptually, we engage the Social Amplification of Risk Framework. Accordingly, Flint residents indeed have higher risk perceptions and report higher negative health impacts compared to residents in surrounding counties. They also report engaging in more health protective behavior. On the contrary, Flint residents express lower levels of trust in entities that are tasked with managing risks. Risk perception, negative health experience, and trust appear as statistically significant correlates of Flint residents’ confidence in their water supply. The salience and variation of attitudes across the region suggests that the water crisis has had ripple effects as predicted by the Social Amplification of Risk Framework.

Research on Random Forest Model and Support Vector Machine Model in Financial Risk Early Warning of Listed Companies

On October 30, 2023, the Central Financial Work Conference was held in Beijing. One of the important contents of the meeting was to prevent and control financial market risks. Because the sustainable development of a company is closely related to the financial market , the company faces increasing financial risk challenges , and it is particularly urgent to establish and optimize an effective financial risk early warning mechanism. The establishment of a financial crisis early warning model can not only enable company managers to adjust the company's development strategy and direction in a timely manner, improve the company's performance, and reduce the company's financial risks, but also predict corporate financial crises, which can help investors evaluate the company's potential value and change the direction of investment. This paper takes the establishment of random forest model as the starting point . First, we understand the theoretical framework of financial risk of listed companies; second, we explain the theoretical basis and advantages of establishing random forest model; then, we deeply explore the theory and empirical analysis of risk indicators; then, we use support vector machine in the specific application of financial risk warning; finally , we get the theoretical analysis and empirical significance of its feature importance, as well as the limitations and future research directions of the method under the fusion of random forest model and support vector machine.

Climate risks, financial performance and lending growth: Evidence from the banking industry

This study examines the impact of climate-related risks, specifically physical and transition risks, on bank performance and lending growth. Using panel data from 147 international banks across 37 countries from 2011 to 2020 and climate data from the Carbon Disclosure Project, our findings show that transition risks positively impact both performance and lending growth, whereas physical risks negatively impact performance and loan growth. Consequently, the inclusion of transition risks in banks' risk frameworks has allowed them to benefit from climate-related policy changes imposed by regulatory bodies, but this does not hold true for physical risks. Although banks recognize the severe impact that physical risks may have on their businesses, they still cannot protect their performance against extreme weather events, particularly because most of these events are characterised by a high degree of uncertainty.