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。     

Dimensions of Market Attractiveness: Competitively Interactive Spatial Models*

This paper presents a normative, multidisciplinary approach for evaluating market entry strategies with concern for the effects of spatial assumptions on performance expectations. An assessment framework is linked to a series of models that show the value of adding spatial and competitive perspectives to typical baseline conceptualizations of market opportunity. Criteria for assessing market attractiveness are discussed with special concern for the problems of field service firms whose market boundaries are not limited by fixed facility locations. The problem is conceptualized as the managerial decision to locate a new brokerage office in a highly competitive regional market area. Realistic constraints are established by focusing the market entry decision through aggregate data from secondary sources that are readily available to an outsider who had not been active in the geographic markets considered. A simple model based on market potential is progressively enhanced with spatially adjusted measures of market attractiveness and competitive resistance. Empirical tests highlight the impact of alternative model formulations and choice criteria on the decision-making process.     

Matching Technology and Organizational Structure:

A case study is presented of a life and health insurance company that undertook a reorganization of work flow, management practices and structure following the implementation of automation. With the adoption of an on-line computer system, there was the potential for a competent, rapidly responsive and adaptive organization. However, the functionally organized, highly specialized business was operating as a white-collar assembly line. It was unable to respond to market demands and financial market changes in a creative, timely manner. The organizational potential created by the total processing system could not be realized until the social system, the organization of the people, was adapted to take full advantages of new technical capabilities. An assessment involving all of top management was conducted in which managers were allowed to determine the problems, goals, and potential solutions. Management developed a long range, overall approach to the organizational change. The decision was made to phase in experimental self managed work teams and to restructure organizational contingencies to support achievement or organizational rather than unit goals. This paper presents the intial twenty-four month period in the process.     

PREDICTING STOCK MARKET BEHAVIOR THROUGH RULE INDUCTION: AN APPLICATION OF THE LEARNING-FROM-EXAMPLE APPROACH*

An artificial intelligence-based rule-induction approach to the analysis of stock market prediction is presented. A single investment analyst was used as the expert for this study. Predicting intermediate fluctuations in the movement of the market for nonconservative investors was selected as the decision to analyze. Commercially available rule-induction software was used to generate rules that predicted the market calls of the market analyst and the actual movements of the market. Rules predicting actual market movement performed better than rules predicting the analyst's calls and better than the analyst himself. Such an approach may prove useful in designing a decision support system for market analysts or in improving the decision-making processes of such analysts. The dynamic nature of the stock market represents a substantially different decision environment than those previously analyzed by learning-from-example (LFE) techniques. This study provides insights into the limits and applications of LFE approaches.     

A Prototype Expert Decision Support System for the Market Appraisal of the Single Family Residence

The assessment of the current market value of residential property is a potential source of anxiety for the typical homeowner. Common criticisms of the existing appraisal process include excessive subjectivity and inconsistency across properties and through time. This paper examines the nature of decision support required for valuation decisions and the appropriateness of applying expert system technologies to evaluate the recoverable value of the single-family residence. The expert system approach allows for the integration of the qualitative and quantitative aspects of appraisal, while introducing the beneficial dimensions of increased objectivity, comprehensiveness, and consistency. A prototype expert system is offered that enables the end user to conduct a market analysis of a subject property. Unlike most expert system applications that seek a diagnostic or classification response, this study explores a numerical intent for the system, in a decision-making environment that is traditionally viewed as highly judgmental. The system's early validation results show promise of proving effective as such an evaluation aid.     

基于疏忽的最优投资决策

研究存在获得、吸收和处理信息的成本时代表性消费者的最优消费和投资决策问题,结果显示成本的存在意味着消费者仅选择在特定时间更新其决策,且在两相邻决策日间保持疏忽。这种理性疏忽的行为特征将直接影响投资决策,进而产生有限参与、处置行为和高储蓄率等现象。模型明确了成本、财富水平等因素对于投资者的消费、投资决策的影响途径及程度,为如何针对不同投资群体合理引导其消费、投资行为以及健全资本市场机制、完善多元化金融服务体制提供了具有可操作性的理论依据和政策建议。同时通过比对相关研究结果,侧面论证了中国市场主要以短期疏忽投资者为主,为研究摩擦市场中的资产价格异动及信息时滞下的政策效应提供了新的视角。     

Market segmentation: A multiple criteria approach combining preference analysis and segmentation decision

We propose a new multiple criteria decision aiding approach for market segmentation that integrates preference analysis and segmentation decision within a unified framework. The approach employs an additive value function as the preference model and requires consumers to provide pairwise comparisons of some products as the preference information. To analyze each consumer’s preferences, the approach applies the disaggregation paradigm and the stochastic multicriteria acceptability analysis to derive a set of value functions according to the preference information provided by each consumer. Then, each consumer’s preferences can be represented by the distribution of possible rankings of products and associated support degrees by applying the derived value functions. On the basis of preference analysis, a new metric is proposed to measure the similarity between preferences of different consumers, and a hierarchical clustering algorithm is developed to perform market segmentation. To help firms serve consumers from different segments with targeted marketing policies and appropriate products, the approach proposes to work out a representative value function and the univocal ranking of products for each consumer so that products that rank in the front of the list can be presented to her/him. Finally, an illustrative example of a market segmentation problem details the application of the proposed approach.     

A statistical framework for strategic decision making with AHP: Probability assessment and Bayesian revision

A probability assessment framework is outlined for an organizational decision involving a conditioning event (CE). The decision may, for example, involve a new-product launch (strategic decision) dependent on the outcome of market research (CE). The framework illustrates how Bayesian revision could be employed as related “news” arrives intermittently to revise current probabilities prior to decision implementation. A unique contribution of this paper is its utilization of the analytic hierarchy process to ascertain a set of consistent and coherent probabilities for the event/sample spaces at all stages of the decision process.     

The Use of the Performance Diagnostic Checklist to Guide Intervention Selection in an Independently Owned Coffee Shop

Abstract

The utility of the Performance Diagnostic Checklist (PDC) (Austin, 2000) as an assessment tool to design an intervention for increasing maintenance tasks in an independently owned coffee shop was examined. The PDC, which was administered to four employees, identified a lack of appropriate antecedents and consequences as areas in need of intervention. Based on the results of the PDC, task clarification and a lottery were implemented in a multiple baseline across tasks design to increase employees' completion of maintenance tasks. The results for task group 1 yielded baseline and intervention means of 44% and 86%, respectively. The results for task group 2 yielded baseline and intervention means of 32% and 67%, respectively. A social validity measure indicated that employees thought that the appearance of the shop had improved, believed the changes helped to improve customer satisfaction, and claimed that the new procedures made their job easier. Overall, results suggest that the PDC can be an effective assessment tool for identifying and subsequently targeting specific areas of improvement within an organization.     

Managing Product Rollovers

We study the product rollover strategy decision, where a firm decides whether to phase out an old generation of a product to be replaced by a new with either a dual or single roll. Our model considers a final build of the old product and preannouncement of the new, and incorporates dynamic pricing and inventory decisions. We find that the optimal price path closely follows changes in reservation price curves for the two products over time. We also identify the drivers of the rollover strategy decision, finding that lower market risk (faster diffusion, higher market responsiveness to preannouncements) and higher performance improvement for the new generation are associated with the single roll strategy.     

An Integrated Scenario Ensemble-Based Framework for Hurricane Evacuation Modeling: Part 1—Decision Support System

This article introduces a new integrated scenario-based evacuation (ISE) framework to support hurricane evacuation decision making. It explicitly captures the dynamics, uncertainty, and human–natural system interactions that are fundamental to the challenge of hurricane evacuation, but have not been fully captured in previous formal evacuation models. The hazard is represented with an ensemble of probabilistic scenarios, population behavior with a dynamic decision model, and traffic with a dynamic user equilibrium model. The components are integrated in a multistage stochastic programming model that minimizes risk and travel times to provide a tree of evacuation order recommendations and an evaluation of the risk and travel time performance for that solution. The ISE framework recommendations offer an advance in the state of the art because they: (1) are based on an integrated hazard assessment (designed to ultimately include inland flooding), (2) explicitly balance the sometimes competing objectives of minimizing risk and minimizing travel time, (3) offer a well-hedged solution that is robust under the range of ways the hurricane might evolve, and (4) leverage the substantial value of increasing information (or decreasing degree of uncertainty) over the course of a hurricane event. A case study for Hurricane Isabel (2003) in eastern North Carolina is presented to demonstrate how the framework is applied, the type of results it can provide, and how it compares to available methods of a single scenario deterministic analysis and a two-stage stochastic program.     

PREFERENCE MAPPING OF PERCEIVED INFORMATION STRUCTURE: IMPLICATIONS FOR DECISION SUPPORT SYSTEMS DESIGN

In a recent issue of this journal, Watkins [13] presented an approach for discovery of decision-maker perceptions of the complexity (dimensionality) of information items that might be supplied by a decision support system. Through use of multidimensional scaling and cluster analysis, relatively homogeneous groups of decision makers, sharing common perceptions of various information items, were formed. This prior research was referred to as a first step in suggesting that information reports could be tailored to groups of decision makers classified on the basis of common perceptions of information. The current research extends the prior study by evaluating decision maker preferences for information in a variety of decision-making scenarios in relation to the previously identified perceptions of the information. Based on the results of the study, conclusions are made which suggest that the tailoring of information to groups of decision makers should be based on both perceptions and preferences for information. Even so, it is demonstrated that the decision tasks have an impact on the preferences for information which may affect the attempt to tailor information to groups of decision makers.     

中国家用轿车初购者与再购者的决策过程差异研究

中国的家用轿车市场正在从以初购者为主的新兴市场向以初购、再购者并重的成熟市场转变.再购者与初购者的购车决策过程存在系统性差异.本研究探索了中国家用轿车初购者与再购者在属性感知一价值判断一态度形成一行为意向这一决策过程的差别.我们通过对北京4802名有购车意向的消费者(2182名初购者与2620名再购者)的调查,发现初购者与再购者在以下四方面存在显著差异:(1)在属性方面,初购者更重视品牌声誉这一外在属性,而再购者更重视汽车的内在属性(内外设计、做工及驾驶性能);(2)在价值方面,初购者更在意车辆的情感价值,而再购者更追求功能价值;(3)在行为方面,初购者更易受周围社会群体的影响,而再购者更听从内心态度的主宰;(4)在购买方面,虽然初购者与再购者都更倾向于购买高销量品牌,但相对于初购者,再购者能更多地尝试低销量品牌.     

存在二手市场时耐用品垄断厂商再制造策略研究

运用稳态均衡分析方法，利用消费者效用模型分析存在二手市场时耐用品垄断厂商再制造策略选择问题。通过模型分析得到，耐用品垄断厂商选择再制造策略的条件为：新耐用品成本、再制造成本以及旧耐用品贬值率低于临界值，而消费者认可程度高于临界值。耐用品垄断厂商选择再制造策略不仅会对新耐用品市场产生挤兑效应，而且也会对二手市场产生挤兑效应。存在旧耐用品再利用率的临界值，当耐用品垄断厂商的旧耐用品再利用率高于该临界值时，选择再制造策略可以提高消费者对耐用品的需求量，产生市场增长效应；新耐用品的生产成本正向影响市场增长效应。     

Exploring uncertainties in a marketplace for cloud computing: a revelatory case study

Today, highly standardized information technology (IT) resources such as storage and processing power are becoming available and affordable to all. Therefore, IT managers evermore focus on reducing the costs and risks that these resources entail rather than on the benefits or competitive edge they provide. A marketplace for cloud computing represents a promising alternative for obtaining standardized IT resources in a highly flexible and scalable manner. Based on a revelatory case study of a cloud market project, we show that uncertainties are prevalent in cloud markets and that the principal-agent theory is an adequate perspective to study and explain these uncertainties. By triangulating data from formal and informal interviews, documentations and project meetings, we develop a second-level contextual understanding of uncertainties in the relationships between market operator, cloud providers and users. Our analysis reveals that while cloud market operators have capabilities to mitigate uncertainties between cloud provider and user, they also cause new uncertainties from the cloud provider and user perspective. As an outcome, we present a framework that sheds light on the uncertainty trade-offs involved in the decision to adopt a cloud market by cloud providers and users.     

Shared planning: a new foundation for quality criteria.

The Chinese word for crisis has two characters. One for danger and one for opportunity. A crisis is a time for awakening to new perspectives and for asking different questions. The widely touted "liability crisis" in the health care field provides just such a time for new approaches. Perhaps there is a way to establish market mechanisms for decision making that gives expression to the desires and values of consumers while respecting the abilities and preferences of physicians. Quality might then be the result of natural selection or, more accurately, of market demand. Such a system would acknowledge that quality in medicine is not for defining. It's for having. Quality should be obtained in bargaining for services, not in mandates of professional regulation.     

Using Expert Models in Human Reliability Analysis—A Dependence Assessment Method Based on Fuzzy Logic

In human reliability analysis (HRA), dependence analysis refers to assessing the influence of the failure of the operators to perform one task on the failure probabilities of subsequent tasks. A commonly used approach is the technique for human error rate prediction (THERP). The assessment of the dependence level in THERP is a highly subjective judgment based on general rules for the influence of five main factors. A frequently used alternative method extends the THERP model with decision trees. Such trees should increase the repeatability of the assessments but they simplify the relationships among the factors and the dependence level. Moreover, the basis for these simplifications and the resulting tree is difficult to trace. The aim of this work is a method for dependence assessment in HRA that captures the rules used by experts to assess dependence levels and incorporates this knowledge into an algorithm and software tool to be used by HRA analysts. A fuzzy expert system (FES) underlies the method. The method and the associated expert elicitation process are demonstrated with a working model. The expert rules are elicited systematically and converted into a traceable, explicit, and computable model. Anchor situations are provided as guidance for the HRA analyst's judgment of the input factors. The expert model and the FES‐based dependence assessment method make the expert rules accessible to the analyst in a usable and repeatable way, with an explicit and traceable basis.     

The Precautionary Principle Versus Risk Analysis

Precautionary behavior serves a valuable protective purpose as a first response to the new. It causes a quick retreat to the safety of the familiar; it provides time for a realistic "friend or foe" assessment of a new event. This rational assessment is often delayed by the sluggishness of government bureaucratic processes, or stopped by an implied challenge to a status quo. At the public level, reassurance may be slow to overcome an early uncertainty. However, a precautionary response does not provide an operational governing principle, although it makes publicly plausible an indefinite concealment of de facto political actions, or nonaction. The alternative of rational decision making at the policy level should flow from a comparative benefit/cost/risk analysis. Such early risk analyses have pragmatic uncertainties based on the limited available knowledge base and, accordingly, require judgmental application.