Risk Management Model Research Articles

A Rank Graduation Box for SAFE AI

The growth of Artificial Intelligence applications requires to develop risk management models that can balance opportunities with risks.We contribute to the development of Artificial Intelligence risk models proposing a Rank Graduation Box (RGB), a set of integrated statistical metrics that can measure the “Sustainability”, “Accuracy”, “Fairness” and “Explainability” of any Artificial Intelligence application.Our metrics are consistent with each other, as they are all derived from a common underlying statistical methodology: the Lorenz curve.The validity of the metrics is assessed by means of their practical application to both simulated and real data. The results from the comparison of alternative machine learning models to simulated data are aligned with the generating models, in general indicating linear regression models as the most accurate, regression tree models as the most fair, Random Forest models as the most robust; and leading to model explanations similar to the true ones from the generating model.The outcomes from the application of Random Forest models to real data show that the proposed RGB metrics are more interpretable and more consistent with the expectations, with respect to standard metrics such as AUC, RMSE and Shapley values. The evidence also shows that the RGB metrics are very general and can be applied to any machine learning method, regardless of the underlying data and model.

Maternal risk-management elucidates the evolution of reproductive adaptations in sharks by means of natural selection

Maternal investment theory is the study of how breeding females allocate resources between offspring size and brood size to achieve reproductive success. In classical trade-off models, r/K-selection and bet-hedging selection, the primary predictors of maternal investments in offspring are population density and resource stability. In crowded, stable environments, K-selected females invest in large offspring at an equivalent cost in brood size. In uncrowded, unstable environments, r-selected females invest in large broods at an equivalent cost in offspring size. In unpredictable resource environments, bet-hedging females invest moderately in brood size and offspring size. The maternal risk-management model represents a profound departure from classical trade-off models. Maternal investments in offspring size, brood size, and brood number are shaped independently by autonomous risk factors: the duration of gaps in resources during seasonal cycles, rates of predation, and unpredictable catastrophic events. To date, no single model has risen to a position of preeminence. Here in sharks, we show that maternal investments within and across species do not agree with the predictions of trade-off models and instead agree with the predictions of the maternal risk-management model. Within and across shark species, offspring size and brood size were independent maternal investment strategies. The risk of starvation favored investments in larger offspring. The risk of predation favored investments in larger broods. If empirical studies continue to confirm its predictions, maternal-risk management may yet emerge as a unifying model of diverse reproductive adaptations by means of natural selection.

A Hybrid Machine Learning and Metaheuristic Based Model for E-Business Risk Management

A Hybrid Machine Learning and Metaheuristic Based Model for E-Business Risk Management

Flare Pollution Loads and Carbon-Dioxide Effect on Rainwater Acidity in Niger-Delta: A Review, Investigation and Model for Safe Living Quarter

Carbon-dioxide does not only affect climate change, but also contribute tremendously in acidification of rain water. Hazard identification and risk assessment are fundamental components of effective risk management, specifically in sensitive areas where adverse effects can have significant consequences. This study provides novel methodology for environmental and safety assessment of flared gases in sensitive areas such as residential homes. Distancing Sampling Technique (DST) was used to investigate the sensitivity of rain water pH at distances away from flare site in order to develop a Risk Management Model for sensitive regions. First, a review on rain water acidity was made around flaring and non-flaring areas in Niger-Delta states, which revealed Moderate-High acidity effect around flaring zones and no effect on non-flaring zone. Secondly, Flared Gas Quantification, pH Experimental Evaluation (PEE) and Risk Assessment Matrix (RAM) were the three systematic approaches used respectively to quantify, measure and evaluate the effects of CO2 and other flare pollutants around the area of study. An average of 809,300,000 Mscf of associated petroleum gases were flared around the oil and gas producing areas in Delta State, causing a release of around 43x106 tons of CO2 from 2012-2022. Experimental results showed the range of pH from 4.56 ± 0.06 to 5.10 ± 0.06 for the 33 samples of harvested rainwater in Kwale community, Delta state causing a deviation of 16.38 to 30.05% from standard. The developed and validated model suggests 4.81KM radius as the safe distance for human habitation from flare sites. Based on these findings, carbon-capture and sequestration projects must be activated in Niger-Delta to curb the menace.

Optimal Resilience and Risk-Driven Strategies for Pre-Disaster Protection of Electric Power Systems against Uncertain Disaster Scenarios

Pre-disaster protection strategies are essential for enhancing the resilience of electric power systems against natural disasters. Considering the budgets for protection strategies, the dependency of other infrastructure systems on electricity, and the uncertainty of disaster scenarios, this paper develops risk-neutral and risk management models of strategies for pre-disaster protection. The risk-neutral model is a stochastic model designed to maximize the expected value of resilience (EVR) of the integrated system. The risk management model is a multi-objective model prioritizing the minimization of risk metrics as a secondary goal alongside maximizing the EVR. A case study conducted on the energy infrastructure systems in the Greater Toronto Area (GTA) validates the effectiveness of the models. The findings reveal the following: (i) increasing the budget enhances the EVR of the integrated system; however, beyond a certain budget threshold, the incremental benefits to the EVR significantly diminish; (ii) reducing the value of the downside risk often results in an increase in the EVR, with the variation in Pareto-optimal solutions between the two objectives being non-linear; and (iii) whether for the risk-neutral or risk management protection strategies, there are reasonable budgets when considering disaster intensity and the cost of protection measures. The models can help decision-makers to select effective protection measures for natural disasters.

Presenting a new deep learning-based method with the incorporation of error effects to predict certain cryptocurrencies

In recent years, with the emergence of blockchain technology, we have witnessed a remarkable increase in the use of digital currencies. However, investing in the digital currency market carries a high level of risk due to the market's erratic behavior and high price fluctuations. Consequently, the need for an appropriate model for intelligent prediction and risk management is perceived. Motivated by the above subject, we propose a novel approach based on a deep neural network with a focus on error patterns. The proposed approach is based on the theory of non-random walks and assumes that there are predictable components in the price movements of cryptocurrencies. This new approach attempts to improve prediction results by modeling residual values and incorporating their impact on the main predictions. The time scope of this research is from October 31, 2018, to December 30, 2023, on a daily basis, spanning Five years. In this study, we utilized Long Short-Term Memory (LSTM) as the main prediction model and Vector Autoregression (VAR) for forecasting noise in three well-known cryptocurrencies: Bitcoin, Ethereum, and Binance Coin (BNB). The results indicate that the proposed approach has been able to enhance the predictions.

Building a Sustainable Future: A Three-Stage Risk Management Model for High-Permeability Power Grid Engineering

Building a Sustainable Future: A Three-Stage Risk Management Model for High-Permeability Power Grid Engineering

Brown seaweed as a food ingredient contributing to an adequate but not excessive amount of iodine in the European diet. A case study with bread.

The large amounts of iodine in brown seaweeds may contribute towards an adequate iodine intake, but also pose a food safety risk. In the current work we estimate the maximum amount of the cultivated brown seaweeds Saccharina latissima and Alaria esculenta (blanched and non-blanched) that can be added to white loaf-type wheat-bread so European consumers are protected against excessive chronic intakes. We use data for high-level consumers of bread with special ingredients added from the EFSA comprehensive European food consumption database to construct a conservative risk management model. We bake prototype seaweed bread and use the output from the model to assess exposure to iodine and trace metals. We also assess some bread quality parameters such as sensory characteristics, crumb firmness and specific volume. The maximum level of iodine in bread that would mitigate the European consumer from excess intakes was 857 μg I kg-1 bread. Assuming a typical 60% wheat flour per kilogram of bread, a maximum amount of 11.3 g of dried blanched A. esculenta (115 mg I kg-1 dry weight) could be incorporated per kilogram of wheat flour into the bread recipe whilst for non-blanched S. latissima, which contained 3500 mg I kg-1 dry weight, only a minuscule 350 mg of seaweed was the limit. For prototype breads, seaweed addition had no significant impact on the specific volume and crumb firmness. Levels of cadmium and arsenic in the bread were also of low toxicological concern. A maximum 1-2% brown seaweed of total flour weight could be added to bread to contribute towards European consumers' adequate iodine intake without overexposure. © 2024 The Author(s). Journal of The Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

A modified geographical weighted regression model for better flood risk assessment and management of immovable cultural heritage sites at large spatial scales

With the increase in extreme climatic events globally in recent years, the increased frequency of flood hazards has had a great impact on immovable cultural heritage sites (ICHs) due to their prolonged exposure to the disaster environment. This poses a risk management challenge, especially on large scales. Most existing flood risk assessment models for ICHs are determined using common natural hazard methods directly and focus less on the characteristics of ICHs. In this paper, we propose a modified geographical weighted regression (MGWR) model to assess flood risk at ICHs, and this model considers the spatial and age properties of the ICHs. These two properties were used for the construction of the weight matrix in the MGWR model. Eleven selected indices and loss survey data with 417 sample points, including 5 types of ICHs, were utilized for model training and testing in Shanxi Province, China. The results showed that the MGWR model had good accuracy with an R2 of 0.928. A comparison between the MGWR and normal GWR models indicated that the accuracies of the older ICHs improved more in the MGWR than in the GWR. We also found that the proposed model performed better than the normal GWR model using age as an index. Moreover, in comparison with three machine learning methods (decision tree, logistic regression, and random forest), the MGWR model still performed better and was less limited by the number of training samples. This paper provides evidence that the characteristics of ICHs are crucial in the construction of flood risk assessment models, and the proposed model can benefit the risk management of various types of ICHs at large spatial scales.

Dynamic incentive mechanisms in mega project-risk management considering the participation of the insurance company

PurposeThe construction of megaprojects often involves substantial risks. While insurance plays an important role as a traditional risk transfer means, owners and insurance companies may still suffer huge losses during the risk management process. Therefore, considering the strong motivation of insurance companies to participate in the on-site risk management of megaprojects, this study aims to propose a collaborative incentive mechanism involving insurance companies, to optimize the risk management effect and reduce the risk of accidents in megaprojects.Design/methodology/approachBased on principal-agent theory, the research develops the static and dynamic incentive models for risk management in megaprojects, involving both the owner and insurance company. The study examines the primary factors influencing incentive efficiency. The results are numerically simulated with a validation case. Finally, the impact of parameter changes on the stakeholders' benefits is analyzed.FindingsThe results indicate that the dynamic incentive model is available to the achievement of a flexible mechanism to ensure the benefits of contractors while protecting the benefits of the owner and insurance company. Adjusting the incentive coefficients for owners and insurance companies within a specified range promotes the growth of benefits for all parties involved. The management cost and economic benefit allocation coefficients have a positive effect on the adjustment range of the incentive coefficient, which helps implement a more flexible dynamic incentive mechanism to motivate contractors to carry out risk management to reduce risk losses.Originality/valueThis study makes up for the absence of important stakeholders in risk management. Different from traditional megaproject risk management, this model uses insurance companies as bridges to break the island effect of risk management among multiple megaprojects. This study contributes to the body of knowledge by designing appropriate dynamic incentive mechanisms in megaproject risk management through insurance company participation, and provides practical implications to both owner and insurance company on incentive contract making, thus achieving better risk governance of megaprojects.

Proposition and Application of a Conceptual Model for Risk Management in Rural Areas: Rural Basic Sanitation Safety Plan (RBSSP)

Proposition and Application of a Conceptual Model for Risk Management in Rural Areas: Rural Basic Sanitation Safety Plan (RBSSP)

Development of Risk Management Model for Research and Development Facilities Construction Project in Johor, Malaysia

The construction industry drives economic growth globally but faces challenges namely outdated practices and inadequate risk management. This research focuses on improving Risk Management in Research and Development (R&D) facilities construction projects, often poorly executed by Project Management Offices (PMOs). Most studies typically address risk identification and assessment, they neglect crucial processes like risk control and monitoring. In pursuit of developing a risk management model for R&D facility construction projects in Johor Industrial Park, Malaysia, conducted a descriptive analysis self-administered questionnaires from professionals in R&D and construction fields with utilizing Statistical Package for the Social Sciences software. Additionally, employed Structural Equation Modelling (illustrated through AMOS graphics) to establish a robust and valid model. The outcome of this research reveals a strong, positive, and significant correlation between PMO requirements of Risk Monitoring and Control Practices, which encompass risk reassessment, risk audits, contingency reserves analysis, risk status meetings and Project Success Factors which related to schedule, cost, facilities requirements, and customer satisfaction in the context of RDD facilities construction. This research successfully tackles the research objectives and developed practicable project risk monitoring and control practices of risk management model for R&D facilities construction projects. Therefore, by consistently integrating these practices into their daily project activities, R&D and construction professionals can mitigate risks and address challenges prevalent in the construction industry, contributing to improved project outcomes.

Analysis of ESG information-disclosure strategies considering different risk-appetite investors

In response to the investment market and public, over 1,000 Chinese listed companies have started to provide environment, society, and governance (ESG) information of their own accord till 2022. How to develop an effective ESG information disclosure mechanism is important for providers of reliable external financing. Here, we designed a risk-management model to describe providers’ information disclosure strategy decisions under different risk-appetite investors, and analyse how information effectiveness, the information sensitivity and risk aversion of investors, and rating agency accuracy affect optimal ESG information-disclosure strategies. We found that: (1) Providers adopt appropriate under-disclosure strategies that can reduce their information collection and disclosure costs, thus maximising the benefits of ESG information disclosure; (2) Investors’ information sensitivity and risk aversion will affect the space for enterprises to adopt under-disclosure strategies; (3) More professional rating agencies can provide stronger credit backing for ESG information, prompting providers to reduce disclosure information.

Developing a security risk management model for commercial private game reserves in the Limpopo Province of South Africa

ABSTRACT This article explores the potential contribution that security risk assessments and a security programme on commercial private game reserves in the Limpopo Province of South Africa can make to ensure the safety and security, not only of their visitors, but also of the wildlife and natural assets of a game reserve. Not all commercial private game reserves can afford an extensive security programme and the person in charge may not be a security and/or a risk management expert, therefore the need arises for the development of a fundamental and straightforward security programme.

Инновационные инструменты и модели управления предпринимательскими рисками в современных условиях

в нынешних условиях актуальность исследования применения инновационного инструментария и моделей, позволяющих управлять предпринимательскими рисками, обусловлена множеством факторов. Один из них связан с высокой степенью неопределённости и невозможностью доведения конструкторских и технологических разработок до практического внедрения. Другой сопряжён с недостаточностью финансирования инновационной деятельности предприятиями (из-за высокой стоимости внедрения и освоения нововведений). Помимо этого, аргументация значимости обращения к теме выстраивается из соображений наличия феномена сопротивления новациям, нехватки квалифицированных кадров, способных управлять соответствующими процессами, трудностей в проведении маркетинговых исследований, необходимости функционирования в компаниях соответствующей организационной структуры управления, недооценённого человеческого капитала. Успешное разрешение этих проблем содействует созданию, финансированию, распространению новых технологий, а также активному процветанию. С учётом обозначенного, в качестве цели автором ставится исследование современных представлений о специфике инновационных инструментов и моделей управления предпринимательскими рисками. Новизна заключается в том, что предложено авторское понимание содержательных сторон модели (блоков), а также алгоритма её формирования и реализации. in the current conditions, the relevance of the study of the use of innovative tools and models that allow managing business risks is due to many factors. One of them is associated with a high degree of uncertainty and the inability to bring design and technological developments to practical implementation. The other is associated with insufficient financing of innovative activities by enterprises (due to the high cost of introducing and mastering innovations). In addition, the argumentation of the importance of addressing the topic is based on considerations of the phenomenon of resistance to innovations, a shortage of qualified personnel capable of managing relevant processes, difficulties in conducting marketing research, the need for companies to operate an appropriate organizational management structure, and underestimated human capital. The successful resolution of these problems contributes to the creation, financing, dissemination of new technologies, as well as active prosperity. Taking into account the above, the author sets as a goal the study of modern ideas about the specifics of innovative tools and models of business risk management. The novelty lies in the fact that the author's understanding of the content aspects of the model (blocks), as well as the algorithm of its formation and implementation, is proposed.

PREDICTION AND RISK MANAGEMENT OF SPREADING FOREST PEST INFESTATIONS USING SATELLITE DATA

The article is devoted to predicting the risk of occurrence of large foci of infection in a pine forest with bark beetles, pathogenic fungi, and nematodes. The areas of disease observed on satellite images have a spotted, clustered structure of drying forest. An important statistical characteristic of the infestation structure is the power law of distribution of infestation clusters in size. Large, catastrophic events have a significant probability in processes with power laws of distributions. The given methods of computer identification and analysis of cluster distributions make it possible to form a statistical percolation model of prediction an d risk management of forest infestation based on information captured (read out) from space images. The only effective means of combating the bark beetle is sanitary felling of the forest. The sanitary cuttings area is considered a control parameter in the model. The model uses forest observation on a lattice of satellite image pixels, similar to the lattice of a percolation system. The universality of the theory is explained by the fact that it considers the interaction of elements of infection clusters, which, near the critical state of a forest ecosystem, obey a power-law distribution. The value of the power-law indicator indicates the formation of large clusters and is used in the model for the risk prediction of infestation development. In the model, risk prediction is understood as a statistical assessment of risk in the future, taking into account changes in the conditions for its manifestation. Changes are determined based on the results of satellite imagery, and the effectiveness of sanitary tree cuttings is considered. An example of a prediction of the development of forest infestations (drying) using images from the Sent inel-2 satellites is presented. Model identification methods are c onsidered, and a test verification of the model is performed. Using scale-invariant indicators of power-law distributions made it possible to abandon expensive high-precision images and replace them with images of average spatial resolution. The approach to synthesizing a prediction and risk management model from space images discussed in the article is based on the theory of self-organized criticality. The model is quite universal and can be used in space geoinformation technologies to orga- nize effective environmental management.

Evaluation of Different Numerical Approaches to Modeling Flood Flows Over Groynes

AbstractThe hydraulic resistance of groynes is an important factor in the determination of design flood water levels on rivers and the assessment of how much these levels are lowered by modifying the groynes. In standard one‐ or two‐dimensional numerical hydrodynamic models for flood risk management, groynes are commonly represented as subgrid features with a local energy loss according to a weir formula. We tested this representation by using a two‐dimensional horizontal mesh at various groyne submergence degrees by comparing the results with those of flume experiments. We also compared the results with simulations using different 2D and 3D approaches on finer grids that incorporate groynes in the bed topography. In one of the two tested 3D models, complete Reynolds‐averaged Navier‐Stokes equations were solved. The second tested 3D model was constructed simpler by assuming hydrostatic pressure distribution in the vertical direction. We employed Delft3D software in construction and execution of all models. One of the 3D models did predict the hydraulic resistance at low submergence better than the standard model, but it slightly underestimated the resistance at higher submergences. Despite differences in flow characteristics, weirs and groynes were found to produce similar flow resistances for the same height and boundary conditions. Simulations of groyne modifications showed that hydraulic resistance decreased nonlinearly with groyne lowering and streamlining.

Application of KMV Model in Credit Risk Management in Banking Industry

As an important part of the national financial system, the banking industry bears important responsibilities for the national economy. In addition, the banking industry is considered an area full of high risks. The risk management of banks not only involves the national finance, economy and national security, but also directly affects the national financial system and the stability of the global financial order. Credit risk has always been one of the risks that domestic and foreign banking banks pay special attention to. Effectively identifying and preventing credit risk is the key to ensure the smooth operation of banks. In order to better identify and manage the credit risk of the listed banks in China, this study uses the KMV model to measure the default distance of the sample banks. Will default distance as assessment of China listed commercial Banks credit risk agent variables, using before 2019 in China's a-share market listed commercial Banks build panel data, empirical analysis, and discuss the analysis results, put forward relevant policy Suggestions, model support for the healthy and steady development of the banking industry. This paper analyzes the current situation of the application of modern credit risk measurement model in the risk management of the banking industry. Meanwhile, combining with the data of some listed banks in China, discusses the credit risks and challenges faced by banks through in-depth analysis, and provides development suggestions with the data analysis of financial model.

Conceptual model of risk management at umk Blitar: ISO 31000

Conceptual model of risk management at umk Blitar: ISO 31000

Collaborative projects: sustainable development and risk management in the corrugated cardboard industry

The high costs of environmentally responsible and socially just approaches are some of the factors that hinder the implementation of sustainable projects in the industrial sector. However, upstream collaborative integration in the corrugated cardboard industry in southeastern Brazil is a reality. In this context, this study aimed to highlight the structure of a collaborative sustainable project in the context of the corrugated cardboard industry, to analyze ESG risk management in the corrugated cardboard industry in the Southeast Region of Brazil, the relationship between ESG risk management and social responsibility in corrugated cardboard industries, the strengths and weaknesses of risk management models in use by the consulted participants, and to propose innovations regarding risk analysis, applicable in sustainable projects with a collaborative bias. The methodology adopted was the case study, with consultation with managers in professional activity in the industrial sector, corroborated by document analysis and systematic review of the literature. We identified preliminary risk analysis (PRA) and failure mode analysis (FMEA) as key practices used by managers in the corrugated paper industry in the region. These practices are insufficient in the convergence of objectives, engagement with the community, and extension of the lifecycle of products and processes. Our findings show that the sustainability of a project may be an extension of the risk analyses carried out in the initial phase, mainly about strategic decision-making and the operationalization of investments. Without bias to the need for risk analysis, the life cycle analysis is also an effective way of highlighting the critical factors, weaknesses, and strengths of a sustainable project. The study indicates the so-called GUT matrix approach (gravity – urgency – tendency) as the most suitable for innovation in risk analyses oriented towards sustainable projects in the analyzed sector.