基于Copula的供应链金融质物组合价格风险测度研究

本文选取白银、铝和铜三种供应链金融质物作为研究对象,在分析三种质物收益率统计特征的基础上,引入Copula模型刻画供应链金融业务中质物收益率的“尖峰厚尾”特征以及质物收益率之间的非线性相关结构;采用Monte Carlo模拟方法测度考虑到极端情况下的质物组合价格风险值CVaR;利用时间平方根法则测度长周期视角下质物组合的价格风险。将CVaR与VaR测度结果进行对比,比较分析短期价格风险与长期价格风险,将Copula模型与传统风险测度方法下计算出的风险值进行对比,以期选取最优测度供应链金融质物组合长期价格风险模型。研究结果表明:从单一质物价格波动特征来看,三种单一质物的收益率均存在非正态分布和“尖峰厚尾”特征,具有一般金融资产收益率分布的特点。从模型的有效性来看,第一,CVaR比VaR能够更好地、全面地测度供应链金融质物组合的价格风险;第二,基于Copula模型的风险测度结果比传统集成风险测度结果的准确性高;第三,平方欧式距离法结果表明在五种Copula模型中,t-Copula是最优刻画供应链金融质物组合收益率间的相依关系的模型。从长短期风险测度结果来看,随着风险期限的增加,质物组合的价格风险值随之增大,以往研究中用短期风险测度往往会低估商业银行所面临的价格风险,不利于商业银行资金信贷的优化配置。得到的结论对我国商业银行开展供应链金融业务防范价格风险提供了量化支持。     

社会网络环境下保护少数意见的风险性大群体应急决策方法

大群体决策过程中,少数意见十分重要,但考虑少数意见又有一定风险性,本文提出了一种社会网络环境下保护少数意见的风险性大群体应急决策方法。首先,利用自然语言处理技术对社交媒体中公众对突发事件的传播信息进行关键词提取,再采用TF-IDF技术提取公众关心的事件属性并确定属性权重;其次,将专家之间的联系考虑到决策当中,构建决策专家之间的社会网络关系;然后,建立少数意见的识别和风险测度机制,并定义了两个风险系数:信任风险系数和偏好风险系数,通过少数意见聚集的信任风险系数调节少数意见聚集的权重,通过偏好风险系数调节群体共识,以得到共识水平较高的大群体决策方案;最后,通过“7.1”宁乡洪灾案例分析,验证了所提方法的可行性和有效性。     

需求可变性降低对均值CVaR约束销售努力决策库存系统的影响

本文运用Levy提出的变换研究需求可变性降低对风险偏好零售商的库存决策、销售努力决策和期望效用的影响,用均值CVaR刻画零售商的风险偏好特性,它包括风险厌恶、风险追求,也具有损失规避的特性。首先,运用该变换定量刻画需求可变性的降低,证明该变换蕴含经典随机占优中的割准则序和二阶随机占优等。其次,给出系统的最优订货量、最优期望效用和最优销售努力水平,得到它们关于风险偏好系数的单调性,并给出降低需求可变性对期望效用的影响。第三,针对风险中性、风险厌恶(最大化CVaR)和风险追求(最小化CVaR)这三种特殊情况得到相应的结果,并给出企业在库存决策和促销决策的管理启示。最后,通过数值例子验证了得到的研究结果并给出相应的管理启示。     

基于贝叶斯网络的船舶港口国监督检查滞留风险研究

针对港口国监督(Port State Control, PSC)检查的复杂性和不确定性, 基于贝叶斯网络理论构建船舶PSC检查滞留风险分析模型. 以东京备忘录(Tokyo MOU)中2014~2017年船舶PSC检查样本数据为基础, 运用R语言bnlearn包进行贝叶斯网络的结构及参数学习. 同时分别执行贝叶斯网络的正向、逆向推理, 定量表示各风险因素与滞留结果之间的相互作用关系, 找出导致船舶滞留的高风险因素, 实现不确定环境下船舶PSC检查滞留风险的全面动态分析. 实证表明, 模型具有较高的精确度, 可为检查人员的滞留决策及航运公司的安全风险管理提供有效依据.     

广义线性模型在汽车延保风险保费测算中的应用

基于保险公司2010年1月—2019年3月的实际保单数据样本,分别运用广义线性模型中的泊松模型和伽玛模型测算出险频率和案均赔款,构建风险保费测算模型,对影响风险保费的因素进行定量研究及分析.结果表明:该方法能够构建多个变量与风险保费的数值关系,减少了信息的损失,得到的费率表可作为实际应用的参考.最后,通过该方法测算结果与市场定价的实例比较对方法的合理性与优越性进行了说明.     

基于银行下侧风险规避的第三方B2B平台激励策略研究

以电子仓单融资为例, 基于银行下侧风险规避角度, 研究联合授信和委托授信下当第三方B2B平台存在行为隐匿的道德风险时, 银行对B2B平台的激励策略设计问题。研究发现:B2B平台的最优努力水平随收益分配比例、回购比例的增大而减小, 随质押率、贷款利率、产品采购量、损失补偿比例的增大而增大;同时银行为规避违约风险, 需设置质押率、贷款利率和贷款额上限及回购比例下限, 并且银行最优收益分配比例与损失补偿比例、最优损失补偿比例与贷款损失率均成正相关关系。此外, 随着B2B平台工作效率的提高, 联合授信下最优收益分配比例将减小, 最优损失补偿比例将增大, 最终近似于委托授信下的最优损失补偿比例。最后给出数值分析。     

基于公众偏好大数据分析的重大突发事件应急决策方案动态调整方法

针对在重大突发事件应急过程中如何根据与其相关的公众偏好大数据信息来对事件进行划分以及确定事件风险大小等问题,提出了一种基于公众偏好大数据分析的两阶段聚类算法,将事件现场公众在社交媒体上发布的偏好大数据信息进行聚类分析,识别出多个与事件相关的子事件,并得出每个子事件的客观风险级别。然后,结合专家经验判断,综合得出每个子事件的风险级别,进而选择相对应的方案。在此基础上,根据实际突发事件多阶段演变特点,描述了应急决策中多事件多方案的动态调整过程,考虑方案之间的相关性和不同子事件调整方案对各风险级别子事件的应急处置效果、应对损失以及不同方案之间的转化成本等因素,得出不同情境下的最佳调整方案。通过案例分析说明了该方法的可行性和有效性。     

Determination,residue and risk assessment of trifloxystrobin,trifloxystrobin acid and tebuconazole in Chinese rice consumption

A simple and rapid analytical method for the detection of trifloxystrobin, trifloxystrobin acid and tebuconazole in soil, brown rice, paddy plants and rice hulls was established and validated by liquid chromatography with tandem mass spectrometry. Acceptable linearity (R² > 0.99), accuracy (average recoveries of 74.3–108.5%) and precision (intra- and inter-day relative standard deviations of 0.9–8.8%) were obtained using the developed determination approach. In the field trial, the half-lives of trifloxystrobin and tebuconazole in paddy plants were 5.7–8.3 days in three locations throughout China, and the terminal residue concentrations of trifloxystrobin and tebuconazole were <100 and 500 μg/kg (maximum residue limits set by China), respectively, at harvest, which indicated that, based on the recommended application procedure, trifloxystrobin and tebuconazole are safe for use on rice. The risk assessment results demonstrated that, owing to risk quotient values of both fungicides being <100%, the potential risk of trifloxystrobin and tebuconazole on rice was acceptable for Chinese consumers. These data could provide supporting information for the proper use and safety evaluation of trifloxystrobin and tebuconazole in rice.     

Residues,dissipation and risk evaluation of spiroxamine in open-field-grown strawberries using liquid chromatography tandem mass spectrometry

The dissipation dynamic and residues of spiroxamine in open-field-grown strawberries were determined using liquid chromatography tandem mass spectrometry (LC–MS/MS). Spiroxamine application was performed according to Egyptian good agricultural practices recommendation. A QuEChERS-based extraction method along with direct analysis with an LC–MS/MS analytical method were optimized and validated, and the specificity of the techniques used was considered satisfactory. Good linearity (R² > 0.999) was obtained for spiroxamine within the range of 0.001–0.1 μg/ml. The mean recoveries varied between 97.1 and 108.2%, with inter- and intra-day precision (RSD) <4.9%. The limit of quantitation for spiroxamine was 0.001 mg/kg. The results indicated that spiroxamine degradation in strawberry followed first–order kinetics (R² > 0.9929) with an estimated half-life value of 4.71 days. Considering the Australian maximum residue limit (0.05 mg/kg) in strawberry and based on the results from residue trials with a preharvest interval of 14 days for strawberry, compliance can be expected. The present results could provide guidance to fully evaluate the risks of spiroxamine residues, preventing any potential health risk to consumers.     

Collective risk models with dependence

In actuarial science, collective risk models, in which the aggregate claim amount of a portfolio is defined in terms of random sums, play a crucial role. In these models, it is common to assume that the number of claims and their amounts are independent, even if this might not always be the case. We consider collective risk models with different dependence structures. Due to the importance of such risk models in an actuarial setting, we first investigate a collective risk model with dependence involving the family of multivariate mixed Erlang distributions. Other models based on mixtures involving bivariate and multivariate copulas in a more general setting are then presented. These different structures allow to link the number of claims to each claim amount, and to quantify the aggregate claim loss. Then, we use Archimedean and hierarchical Archimedean copulas in collective risk models, to model the dependence between the claim number random variable and the claim amount random variables involved in the random sum. Such dependence structures allow us to derive a computational methodology for the assessment of the aggregate claim amount. While being very flexible, this methodology is easy to implement, and can easily fit more complicated hierarchical structures.