风险偏好与属性约简在决策问题中的应用研究

将决策者风险偏好与属性约简算法应用到具有大量属性的决策问题,提出先对决策者分类再进行决策的策略． 根据决策者的风险偏好特征将其分为风险规避型、风险中立型、风险偏好型,针对不同类型的决策者分别采取相应的算法,提取有效属性并利用有效属性进行决策; 针对不同风险偏好的决策者,提出相应的风险偏好预期规则; 提出基于优势关系辨析矩阵的属性赋权算法及基于属性值优势度矩阵的进行信息融合与排序算法; 最后通过属性值为实数与区间数的两个实际案例表明该算法的科学合理性．     

基于前景理论的多阶段混合信息决策方法

针对属性值为混合信息的多阶段决策问题,考虑决策者风险偏好态度,提出一种新的基于动态参考点的前景理论决策方法。通过定义直觉模糊熵,将混合信息一致化为信息效用值,并在传统单阶段参考点设置方法的基础上引入目标参考点,综合发展状态和发展趋势计算得到具有决策者风险偏好波动特点的动态参考点;进一步通过熵权法确定属性的权重范围,并构建考虑偏差度的目标优化模型,在引入前景理论的基础上测算各备选方案的动态前景值。将该决策方法应用到商业银行对小微企业贷款融资的选择案例中,对比分析说明方法的合理性和可行性。     

基于心理阈值的多属性决策问题目标调整研究

将决策者在决策指标上存在心理阈值的现状应用到多属性决策问题,提出先对决策目标调整再进行决策的方法。首先,对效益型、成本型、中间型指标构建相应的指标满意度函数和算法,针对不同类型的指标选择相应的算法,计算决策者在每个备选方案存在心理阈值属性上的满意度;其次,根据决策者满意度与心理阈值,调整决策目标组建新的决策信息表;再次,提出基于决策者满意度的属性赋权与信息集结算法模型,获得最优决策方案;最后,通过一个实际生活中的决策者购房案例,表明该方法的科学合理性。     

基于贝叶斯网络推理的双重不确定信息集结模型

针对一类不确定多属性决策问题,提出了基于贝叶斯网络推理的信息集结决策模型。根据决策依据信息,建立了决策方案综合属性值优劣的范围估计模型;由影响方案属性的因素构成的贝叶斯网络拓扑结构图,建立了基于贝叶斯推理的方案综合属性值确定模型;基于两类信息的内在关联性,提出了两种结果集结的最大相似度模型,最后得出方案综合属性值,算例表明基于贝叶斯网络推理的双重不确定信息集结模型是有效的。     

基于语言评价信息的快速集结方法研究

针对具有语言评价信息的多指标群决策问题,研究了基于二元语义的快速集结方法。把各决策者的语言评价信息转化为二元语义矩阵;依据各决策者的判断偏好,提出方案属性权重求解的规划模型;通过集结和比较各决策者偏好和总体偏好的差异,提出决策者权重确定模型;定义决策者判断一致度及决策者偏差的查找算法,快速辨别偏差较大的决策者并对其提供偏好调整建议;文后例子将其应用于某危险品的救险应急方案的选择。     

多属性决策决问题的满意度与赋权研究

多属性决策问题的决策中,决策者往往对属性上的数值存在一定的心理预期。首先,通过心理预期与实际数据获得决策对象在每个属性上的满意度,对决策对象进行筛选过滤;其次,提出属性值信息相容关系,利用属性值之间的相容度进行赋权,信息融合对满足决策者心理预期的决策对象排序择优;再次,提出决策对象满意度,并指出传统的排序方法获取的最优决策对象与决策者总体满意度最大的决策对象并不等价。具体算例表明,该方法科学有效且可行。     

语言多属性决策的目标规划模型

研究了只有部分属性权重信息、属性值以语言变量或不确定语言变量形式给出且决策者对方案有偏好信息的语言多属性决策问题.给出了语言变量和不确定语言变量的运算法则,以及不确定语言变量之间比较的可能度公式,定义了语言变量的偏离度概念.在属性值以1)语言变量和2)不确定语言变量,这两种形式给出的情形下,分别建立了一个基于偏离度的目标规划模型,并通过求解这两种模型分别获得相应的属性权重.然后对于情形1),利用语言加权平均(LWA)算子,对语言决策信息进行加权集成,继而对方案进行排序和择优;对于情形2),利用不确定语言加权平均(ULWA)算子,对不确定语言决策信息进行加权集成,并利用可能度公式构造可能度矩阵(互补判断矩阵),继而利用互补判断矩阵排序公式对决策方案进行排序和择优.最后进行了实例分析.     

方案有不确定偏好的区间数相对熵群决策方法

研究了属性值是区间数并且已知方案偏好信息的多属性群决策问题。建立了每个方案客观偏好值与主观偏好值偏差的相对熵测度矩阵;基于客观信息和方案偏好信息的相对熵建立了属性权重模型;建立了一个新的区间数比较的可能度公式,基于可能度公式给出了方案排序方法,算例说明方法可行性。     

区间概率条件下属性值为不确定语言变量的风险型多属性决策研究

针对区间概率条件下属性值为不确定语言信息且属性权重未知的风险型多属性决策问题,提出了一种基于概率理论和不确定语言变量的TOPSIS决策方法。首先建立了区间概率转化为点概率的数学模型,通过期望值将风险型决策矩阵转化为确定型矩阵;然后利用方案与理想解越近方案越优,与负理想解越远方案越优的原则建立属性权重确定模型,并利用TOPSIS方法的相对优属度大小确定方案的排序;最后通过应用案例说明了本方法的决策步骤。     

对方案有偏好的区间数多属性灰色关联决策模型

针对属性值以区间数形式给出并且已知方案偏好信息的多属性决策问题,提出了一种灰色关联分析的决策方法。该方法依据一般的灰色关联分析方法的基本思路,给出了该问题的计算步骤,其核心是通过构建并求解一个单目标最优化模型,得到属性权重信息,从而计算出每个方案客观偏好值与主观偏好值的灰色关联系数,进而得到每个方案客观偏好与主观偏好的关联度,根据关联度对所有方案进行排序。最后给出了一个数值例子,结果表明方法简单,有效和易于计算。     

二分群体决策规则的序性质研究

Karotkin等发现二分群体决策的加权多数决策规则集具有序性质,但未能解释其原因.文章提出了规则链和规则距离函数的概念,指出当一组决策规则构成规则链时这组规则便具有序性质,从而解释了这一现象.而判断一组规则是否构成规则链则可以通过计算各规则间的规则距离来实现.随后通过对具体实例的分析进一步阐述了得到的结论.     

Mingling decision making metaphors

Organizational decisions provide conceptual playing fields wherein scientists adhering to rival theories based on different metaphors skirmish in-decisively. Organizational decisions, however, are also empirical arenas wherein practitioners espousing discordant theories-in-use reconcile their differences pragmatically. Practitioners' decision-making metaphors encountered while studying capital budgeting suggest how disjoint perspectives are assimilated and shifts from instrumental to symbolic actions are triggered. Implications for decision theories are discussed, and potential benefits of incorporating practitioners' knowledge into organizational science are considered.     

The strategic divestment decision

Management, periodicals have of late been reflecting the increasing attention corporate managers are paying to the difficult problem of divestment. The purpose of this paper is to outline conceptually a planning and analytical framework for dealing with divestments.Corporate Planners in manufacturing organizations will find particular relevance in the author's comments.     

Hospital leasing decision models

This paper adapts leasing decision models to the hospital case. The appropriate use of alternative formulations is considered in conjunction with an example from the hospital literature. Finally, certain theoretical problems of leasing in a nonprofit environment are considered.     

Sequential multi-criterion decision making

In this paper we consider a simple sequential multicriterion decision making problem in which a decision maker has to accept or reject a series of multi-attributed outcomes. We show that using very simple programming techniques, a great deal of the decision making can be automated. The method might be applicable to situations in which a dealer is having to consider sequential offers in a trading market.     

California's Wickline decision revisited

In a recent California appellate decision, Wilson v. Blue Cross of Southern California, 222 Cal. App 3d 660, 271 Cal Rptr 876 (2d Dist., 1990), the court cut back on its earlier decision in Wickline v. State of California, 192 Cal. App. 3d 1630, 239 Cal Rptr 810 (2d Dist. 1986), which had provided substantial protection for third-party payers against liability for utilization review decisions. The Wilson decision not only limits Wickline to its particular facts, but also criticizes some of its rationale.     

最优保险投资决策

2005年初我国对保险公司直接进入资本市场进行投资开始放开.如何选择最佳的投资策略就成为目前保险公司所面临的难题,而传统的投资模型的诸多不足使得它在实际应用中有很大局限性.讨论的模型克服了传统模型的不足.在该模型中,索赔是一个复合Poisson过程,保险公司可选择与投资期内的安全要求相一致的投资比例.应用最优控制原理求解模型得到了最优投资策略以及有效边界的解析形式,并讨论了承保收益和承保风险对投资策略与有效边界的影响.     

Taxonomy of outsourcing decision models

This article proposes a taxonomy of outsourcing decision models. The proposed taxonomy may assist practitioners in their decision-making and researchers in the identification, evaluation and classification of decision models. Further, this article also provides an overview and evaluation of existing outsourcing decision models, and assesses them for their applicability to the outsourcing decision process. In particular, this article finds that the outsourcing decision models proposed in the literature have limitations in their applicability to the outsourcing decision process.     

Intelligence gathering for decision making

Empirical studies of decision making seldom consider the intelligence gathering activities required for decision making. In an attempt to fill this void, this study set out to identify and assess some of the key steps in gathering intelligence, considering the difficulty of the decision and available resources. The study found performance gapping and premising to be crucial activities and explored how each is carried out. A variety of premising and gapping tactics were uncovered, with some having better success than others. These tactics were found to influence the search approach selected to uncover alternatives and the success of the resulting decision. The best results were noted when search efforts are guided by needs documented with a quantitative performance gap; and when formal search or negotiation is used to identify alternatives. These findings hold for decisions that have high and low difficulty and for those with high and low resource support. The implications of these findings for decision makers and decision making are discussed.