Public Values in Risk Debates

Both the issues inherent in regulation of specific risks and the contexts in which such regulatory processes occur are often characterized by confusion and controversy. Tools based on multiattribute utility measurement (MAUT) can help to clarify public values in risk debates and thus to facilitate option invention and decision making. Stakeholder group representatives, in interaction with an analyst, structure their values relevant to the problem into a value tree. The analyst prepares a common tree, iterating until all stakeholder representatives accept it. Stakeholders express their values as weights on the common tree. This provides a basis for option invention and negotiation. The paper presents three illustrative applications.     

Ranking the Risks from Multiple Hazards in a Small Community

Natural hazards, human-induced accidents, and malicious acts have caused great losses and disruptions to society. After September 11, 2001, critical infrastructure protection has become a national focus in the United States and is likely to remain one for the foreseeable future. Damage to the infrastructures and assets could be mitigated through predisaster planning and actions. A systematic methodology was developed to assess and rank the risks from these multiple hazards in a community of 20,000 people. It is an interdisciplinary study that includes probabilistic risk assessment (PRA), decision analysis, and expert judgment. Scenarios are constructed to show how the initiating events evolve into undesirable consequences. A value tree, based on multi-attribute utility theory (MAUT), is used to capture the decisionmaker's preferences about the impacts on the infrastructures and other assets. The risks from random failures are ranked according to their expected performance index (PI), which is the product of frequency, probabilities, and consequences of a scenario. Risks from malicious acts are ranked according to their PI as the frequency of attack is not available. A deliberative process is used to capture the factors that could not be addressed in the analysis and to scrutinize the results. This methodology provides a framework for the development of a risk-informed decision strategy. Although this study uses the Massachusetts Institute of Technology campus as a case study of a real project, it is a general methodology that could be used by other similar communities and municipalities.     

Tree‐Based Logistic Regression Approach for Work Zone Casualty Risk Assessment

This study presents a tree‐based logistic regression approach to assessing work zone casualty risk, which is defined as the probability of a vehicle occupant being killed or injured in a work zone crash. First, a decision tree approach is employed to determine the tree structure and interacting factors. Based on the Michigan M‐94\I‐94\I‐94BL\I‐94BR highway work zone crash data, an optimal tree comprising four leaf nodes is first determined and the interacting factors are found to be airbag, occupant identity (i.e., driver, passenger), and gender. The data are then split into four groups according to the tree structure. Finally, the logistic regression analysis is separately conducted for each group. The results show that the proposed approach outperforms the pure decision tree model because the former has the capability of examining the marginal effects of risk factors. Compared with the pure logistic regression method, the proposed approach avoids the variable interaction effects so that it significantly improves the prediction accuracy.     

Quantifying Uncertainty in a Risk Assessment Using Human Data

A call for risk assessment approaches that better characterize and quantify uncertainty has been made by the scientific and regulatory community. This paper responds to that call by demonstrating a distributional approach that draws upon human data to derive potency estimates and to identify and quantify important sources of uncertainty. The approach is rooted in the science of decision analysis and employs an influence diagram, a decision tree, probabilistic weights, and a distribution of point estimates of carcinogenic potency. Its results estimate the likelihood of different carcinogenic risks (potencies) for a chemical under a specific scenario. For this exercise, human data on formaldehyde were employed to demonstrate the approach. Sensitivity analyses were performed to determine the relative impact of specific levels and alternatives on the potency distribution. The resulting potency estimates are compared with the results of an exercise using animal data on formaldehyde. The paper demonstrates that distributional risk assessment is readily adapted to situations in which epidemiologic data serve as the basis for potency estimates. Strengths and weaknesses of the distributional approach are discussed. Areas for further application and research are recommended.     

基于改进教学式方法的可解释信用风险评价模型构建

信用风险评价是金融机构风险防控的重要环节之一。近年来，基于机器学习的信用风险评价模型以其准确的预测效果受到越来越多的关注，但机器学习模型具有可解释性不强的弊端，导致投资者无法完全信任其预测结果。针对上述问题，本文提出了一种改进的教学式方法，利用机器学习模型指导生成一个兼顾准确性与可解释性的信用风险评价决策树模型，以辅助投资者决策。为提高决策树对机器学习模型中正确功能的学习能力，提出了基于Weight Synthetic Minority Over-sampling Technique（Weight-SMOTE）的伪数据集生成方法，以提高伪数据集中可信度高的功能所标记的伪样本比例；为实现所生成的决策树在准确性、可解释性以及其与机器学习模型一致性间的有效权衡，在决策树生成过程中提出了一种新的决策树剪枝方法；同时针对保真度评价指标的局限性，提出了真保真度评价指标，来有效的衡量决策树与机器学习模型正确功能的近似程度。最后使用3个真实信用风险评价数据集对改进的教学式方法进行验证，实验结果表明所提出方法能够生成准确且可解释的信用风险评价模型，以满足投资者的决策偏好与实际需求。     

A comparison of simplified value function approaches for treating uncertainty in multi-criteria decision analysis

Uncertainty is present in many decisions where an action's consequences are unknown because they depend on future events. Multi-attribute utility theory (MAUT) offers an axiomatic basis for choice, but practitioners may prefer to use simpler decision models for transparency, ease of use, or other practical reasons. We identify some ‘simplified’ models currently in use and use a simulation experiment to evaluate their ability to approximate results obtained using MAUT. Our basic message is that avoiding assessment errors in the application of a simplified model is more important than the choice of a particular type of model, but that the best performance over a range of decision problems is from a model using a small number of quantiles.     

A Tiered Approach for Risk‐Benefit Assessment of Foods

Risk‐benefit analyses are introduced as a new paradigm for old problems. However, in many cases it is not always necessary to perform a full comprehensive and expensive quantitative risk‐benefit assessment to solve the problem, nor is it always possible, given the lack of required date. The choice to continue from a more qualitative to a full quantitative risk‐benefit assessment can be made using a tiered approach. In this article, this tiered approach for risk‐benefit assessment will be addressed using a decision tree. The tiered approach described uses the same four steps as the risk assessment paradigm: hazard and benefit identification, hazard and benefit characterization, exposure assessment, and risk‐benefit characterization, albeit in a different order. For the purpose of this approach, the exposure assessment has been moved upward and the dose‐response modeling (part of hazard and benefit characterization) is moved to a later stage. The decision tree includes several stop moments, depending on the situation where the gathered information is sufficient to answer the initial risk‐benefit question. The approach has been tested for two food ingredients. The decision tree presented in this article is useful to assist on a case‐by‐case basis a risk‐benefit assessor and policymaker in making informed choices when to stop or continue with a risk‐benefit assessment.     

Risk Prevention and Policy-Making in Automatic Systems

Accidents with automatic production systems are reported to be on the order of one in a hundred or thousand robot-years, while fatal accidents are found to occur one or two orders of magnitude less frequently. Traditions in occupational safety tend to seek for safety targets in terms of zero severe accidents for automatic systems. Decision-making requires a risk assessment balancing potential risk reduction measures and costs within the cultural environment of a production company. This paper presents a simplified procedure which acts as a decision tool. The procedure is based on a risk concept approaching prevention both in a deterministic and in a probabilistic manner. Eight accident scenarios are shown to represent the potential accident processes involving robot interactions with people. Seven prevention policies are shown to cover the accident scenarios in principle. An additional probabilistic approach may indicate which extra safety measures can be taken against what risk reduction and additional costs. The risk evaluation process aims at achieving a quantitative acceptable risk level. For that purpose, three risk evaluation methods are discussed with respect to reaching broad consensus on the safety targets.     

Modeling Correlated Discrete Uncertainties in Event Trees with Copulas

Modeling the dependence between uncertainties in decision and risk analyses is an important part of the problem structuring process. We focus on situations where correlated uncertainties are discrete, and extend the concept of the copula‐based approach for modeling correlated continuous uncertainties to the representation of correlated discrete uncertainties. This approach reduces the required number of probability assessments significantly compared to approaches requiring direct estimates of conditional probabilities. It also allows the use of multiple dependence measures, including product moment correlation, rank order correlation and tail dependence, and parametric families of copulas such as normal copulas, t‐copulas, and Archimedean copulas. This approach can be extended to model the dependence between discrete and continuous uncertainties in the same event tree.     

Measurement and Pricing of Risk in Insurance Markets

The theory and practice of risk measurement provides a point of intersection between risk management, economic theories of choice under risk, financial economics, and actuarial pricing theory. This article provides a review of these interrelationships, from the perspective of an insurance company seeking to price the risks that it underwrites. We examine three distinct approaches to insurance risk pricing, all being contingent on the concept of risk measures. Risk measures can be interpreted as representations of risk orderings, as well as absolute (monetary) quantifiers of risk. The first approach can be called an "axiomatic" one, whereby the price for risks is calculated according to a functional determined by a set of desirable properties. The price of a risk is directly interpreted as a risk measure and may be induced by an economic theory of price under risk. The second approach consists in contextualizing the considerations of the risk bearer by embedding them in the market where risks are traded. Prices are calculated by equilibrium arguments, where each economic agent's optimization problem follows from the minimization of a risk measure. Finally, in the third approach, weaknesses of the equilibrium approach are addressed by invoking alternative valuation techniques, the leading paradigm among which is arbitrage pricing. Such models move the focus from individual decision takers to abstract market price systems and are thus more parsimonious in the amount of information that they require. In this context, risk measures, instead of characterizing individual agents, are used for determining the set of price systems that would be viable in a market.     

Risk of Extreme Events in Multiobjective Decision Trees Part 1. Severe Events

Earlier work with decision trees identified nonseparability as an obstacle to minimizing the conditional expected value, a measure of the risk of extreme events, by the well-known method of averaging out and folding back. This first of two companion papers addresses the conditional expected value that is defined as the expected outcome assuming the exceedance of a threshold β, where β is preselected by the decision maker. An approach is proposed to overcome the need to evaluate all policies in order to identify the optimal policy. The approach is based on the insight that the conditional expected value is separable into two constituent elements of risk and can thus be optimized along with other objectives, including the unconditional expected value of the outcome, by using a multiobjective decision tree. An example of sequential decision making for improving highway capacity is given.     

A Dynamic Model to Assess Microbial Health Risks Associated with Beneficial Uses of Biosolids

There is increasing interest in the development of a microbial risk assessment methodology for regulatory and operational decision making. This document presents a methodology for assessing risks to human health from pathogen exposure using a population-based model that explicitly accounts for properties unique to an infectious disease process, specifically secondary transmission and immunity. To demonstrate the applicability of this risk-based method, numerical simulations were carried out for a case study example in which the route of exposure was direct consumption of biosolids-amended soil and the pathogen present in the soil was enterovirus. The output from the case study yielded a decision tree that differentiates between conditions in which the relative risk from biosolids exposure is high and those conditions in which the relative risk from biosolids is low. This decision tree illustrates the interaction among the important factors in quantifying risk. For the case study example, these factors include biosolids treatment processes, the pathogen shedding rate of infectious individuals, secondary transmission, and immunity. Further refinement in methods for determining biosolids exposures under field conditions would certainly increase the utility of these approaches.     

Risk of Extreme Events in Multiobjective Decision Trees Part 2. Rare Events

Earlier work with decision trees identified nonseparability as an obstacle to minimizing the conditional expected value, a measure of the risk of extreme events, by the well-known method of averaging out and folding back. This second of two companion papers addresses the conditional expected value that is defined as the expected outcome assuming that a random variable is observed only in the upper 100 (1 −α) percent of potential outcomes, where α is a cumulative probability preselected by the decision maker. An approach is proposed to overcome the need to evaluate all policies in order to identify the optimal policy. The approach is based in part on approximating the conditional expected value by using statistics of extremes. An existing convenient approximation of the conditional expected value is shown to be separable into two constituent elements of risk and can thus be optimized, along with other objectives including the unconditional expected value of the outcome, in a multiobjective decision tree. An example of sequential decision making for remediation or environmental contamination is provided. The importance of the results for risk analyis beyond the minimization of conditional expected values is pointed out.     

基于VPRS的软件项目投标风险规避群决策研究

设计了一个基于变精度粗糙集的模型算法,用于调整软件项目投标风险群决策表中的分类误差,为了全面反映专家的个人能力和在群决策过程中的公正、认真程度,赋予每个专家相应的权重,计算投标项目和风险指标的综合风险当量,并讨论了相应的风险规避措施、风险规避力度排序和风险规避流程。     

Integrated Uncertainty Analysis for Ambient Pollutant Health Risk Assessment: A Case Study of Ozone Mortality Risk

The U.S. Environmental Protection Agency (EPA) uses health risk assessment to help inform its decisions in setting national ambient air quality standards (NAAQS). EPA's standard approach is to make epidemiologically‐based risk estimates based on a single statistical model selected from the scientific literature, called the “core” model. The uncertainty presented for “core” risk estimates reflects only the statistical uncertainty associated with that one model's concentration‐response function parameter estimate(s). However, epidemiologically‐based risk estimates are also subject to “model uncertainty,” which is a lack of knowledge about which of many plausible model specifications and data sets best reflects the true relationship between health and ambient pollutant concentrations. In 2002, a National Academies of Sciences (NAS) committee recommended that model uncertainty be integrated into EPA's standard risk analysis approach. This article discusses how model uncertainty can be taken into account with an integrated uncertainty analysis (IUA) of health risk estimates. It provides an illustrative numerical example based on risk of premature death from respiratory mortality due to long‐term exposures to ambient ozone, which is a health risk considered in the 2015 ozone NAAQS decision. This example demonstrates that use of IUA to quantitatively incorporate key model uncertainties into risk estimates produces a substantially altered understanding of the potential public health gain of a NAAQS policy decision, and that IUA can also produce more helpful insights to guide that decision, such as evidence of decreasing incremental health gains from progressive tightening of a NAAQS.     

When Costs Are Unequal and Unknown: A Subtree Grafting Approach for Unbalanced Data Classification*

In binary classifications, a decision tree learned from unbalanced data typically creates an important challenge related to the high misclassification rate of the minority class. Assigning different misclassification costs can address this problem, though usually at the cost of accuracy for the majority class. This effect can be particularly hazardous if the costs cannot be specified precisely. When the costs are unknown or difficult to determine, decision makers may prefer a classifier with more balanced accuracy for both classes rather than a standard or cost‐sensitively learned one. In the context of learning trees, this research therefore proposes a new tree induction approach called subtree grafting (STG). On the basis of a real bank data set and several other data sets, we test the proposed STG method and find that our proposed approach provides a successful compromise between standard and cost‐sensitive trees.     

Airline corporate planning— a conceptual framework

In the current economic recession, efficient planning is of paramount importance. This paper constructs a conceptual framework for the long term corporate planning of an airline: the framework suggested is an integrated approach rather than the divisional one that is widespread in the industry. The paper attempts to identify the long-term objectives of an airline, the various types of constraints under which it must operate, and the decision variables that are under its control.     

Functional and Behavioral Application

Simulation techniques have been recommended in the recent literature as vehicles for improving the analysis of the corporate capital budgeting decision. Such techniques are alleged to provide more helpful measures of both return and risk than do single-point discounted cash flow estimates of project worth. This contention is challenged here. The conclusion is reached that the information provided by simulation is, at best, no better than is generated by the traditional single-point present value approach and, in one very important respect, is markedly inferior.     

Project risk management using multiple criteria decision-making technique and decision tree analysis: a case study of Indian oil refinery

This study proposes an integrated analytical framework for effective management of project risks using combined multiple criteria decision-making technique and decision tree analysis. First, a conceptual risk management model was developed through thorough literature review. The model was then applied through action research on a petroleum oil refinery construction project in the Central part of India in order to demonstrate its effectiveness. Oil refinery construction projects are risky because of technical complexity, resource unavailability, involvement of many stakeholders and strict environmental requirements. Although project risk management has been researched extensively, practical and easily adoptable framework is missing. In the proposed framework, risks are identified using cause and effect diagram, analysed using the analytic hierarchy process and responses are developed using the risk map. Additionally, decision tree analysis allows modelling various options for risk response development and optimises selection of risk mitigating strategy. The proposed risk management framework could be easily adopted and applied in any project and integrated with other project management knowledge areas.     

Integrating performance and risk aspects of supply chain design processes

Abstract

Supply chain design is a complex and relatively poorly structured process, involving choosing many decisional parameters and it usually requires consideration of numerous sources of uncertainty. Many conventional processes of supply chain design involve taking a deterministic approach, using point estimates, on important measures of supply chain effectiveness such as cost, quality, delivery reliability and service levels. Supply chain disruptions are often separately considered as risks, both in the research literature and in practice, meaning that a purely traditional risk management and risk minimization approach is taken. We have developed and applied an approach that combines the intellect and experience of the supply chain designer with the power of evaluation provided by a Monte Carlo simulation model, which uses decision analysis techniques to explicitly incorporate the full spectrum of uncertain quantities across the set of alternative supply chain designs being considered. After defining and setting out the general decision variables and uncertainty factors for 16 distinct supply chain design decision categories, we then apply that approach to combine the decision-makers’ heuristics with the probabilistic modeling approach, iteratively, to achieve the best of both elements of such an approach. This novel approach to fully integrating performance and risk elements of supply chain designs is then illustrated with a case study. Finally, we call for further developmental research and field work to refine this approach.