Skip to content

GRA · 精算与量化风险

空间金融资本与危害、风险暴露和转型的交汇之处

可信度与稀疏数据

Many risks have little data: new products, small portfolios, rare perils and emerging markets. Credibility theory blends a portfolio’s own experience with wider data according to how much the own data can be trusted. Bayesian methods, pooling and expert judgement extend this. This page sets out how actuaries estimate risk with sparse data, where estimates go wrong, the sources used and who decides.

01登记

Credibility and sparse data on the record.

02问题

可信度与稀疏数据:风险如何发展。

在损失历史较短或缺失的情况下开展工作。下方档案说明风险如何发展、衡量什么、数据来自何处、如何建模以及由谁决定。

机制

自有数据与更广泛数据的融合

可信度权重随着自身经验的增加而赋予其更大权重。权重过小会忽略真实差异;权重过大则会按噪声定价。

机制

Benchmarks may not fit

行业或再保险人基准反映的是其他投资组合。如果投资组合在构成或做法上不同,混合后的结果会带有偏差。

机制

专家判断填补空白

Where data are absent, structured expert elicitation provides estimates. Without structure and documentation, judgement adds hidden bias.

机制

随数据到来而更新

贝叶斯更新 随着经验积累修正估计,显示数据使先验假设发生了多大变化。

03空间金融

对照其起赔点的干旱指数。

如何对照干旱保险开始赔付的临界点来解读旱季。季节和设计条款均为合成数据。

萨赫勒地区的一个雨季,对照干旱保障开始赔付和停止赔付的节点进行解读。合成的季节和设计条款;不意味着任何保障。
04指标

衡量什么,以及衡量得如何。

每个指标都注明其单位、频率、背后的来源类型以及数值将附带的证据标签。此处不显示数值:数值由计划依据其自身权限提供。

指标单位节奏来源类型标签
Credibility weight assigned to own experienceproportion, zero to one每次分析定价分析模型估算
Exposure underlying own experience风险暴露单位每次分析投资组合数据观测
Difference between own and benchmark estimates百分比每次分析定价分析估算
Expert elicitation sessions documented计数每个模型模型文档已声明
关键参数的后验不确定性区间宽度每次分析贝叶斯模型模型估算
上线后的实际与预期之比比率定期经验监测估算
05孪生与级联模拟器

Trace a shock in credibility and sparse data to the balance sheet.

Assembled from the Nexus Standards area profile Insurance and reinsurance: the shocks it names, the systems and sectors that carry the loss, the controls that dampen it and the data that observe it. Pick an initiating shock and step through the cascade to see which exposures it reaches and where losses could concentrate. The Map view places the run on an example geography with open data. Every weight is a stated assumption. An exercise, not a forecast, a valuation, a rating or investment advice. To model a place of your own choosing, open the full System Builder.

灾害

  • 热带气旋
  • 地震
  • 冰塞洪水
  • 野火
  • 风暴潮(在下游引发)
  • 强降雨(在下游引发)
  • 河流洪水(在下游引发)
  • Flash flood (set off downstream)
  • 危险海浪(在下游引发)
  • 大范围停电(在下游引发)
  • 大规模流离失所(在下游引发)
  • 沿海洪水(在下游引发)
  • Aftershock sequence (set off downstream)
  • Fault surface rupture (set off downstream)
  • Soil liquefaction (set off downstream)
  • Slope slide (set off downstream)
  • Rockfall (set off downstream)
  • Tsunami (set off downstream)

控制措施

  • NS-0 章程与原则
  • NS-3 风险记录 UNI(语法、旧编码对照、分配机构)
  • NS-9 情境 UNI(部署、实例、计划实例)
  • NS-10 政策和条款(机器可读的义务:定义、约束、评估和执行)
  • NS-11 验证与监测(证据、证明、零信任符合性观测)
  • NS-14 符合性及与外部标准的对照
  • NRS-F3 保险、巨灾风险与保护缺口
  • NRS-H113 危害类别:金融体系脆弱性(NHS-1 soc.financial-system)
  • NRS-U17Universe 平台概况:Insurance Nexus
  • NRS-H71 危害类别:深时与宇宙灾难(NHS-1 planet.deep-time)
  • NRS-H65 危害类别:超越行星边界(NHS-1 planet.boundary)
  • NRS-F8 参数化与指数型风险转移

观测

  • OECD Data Explorer (incl. Creditor Reporting System, insurance and pension statistics) (listed for reference)
  • Insurance statistics (listed for reference)
  • USGS earthquake GeoJSON summary feeds (listed for reference)
  • Direct economic loss attributed to disasters in relation to global gross domestic product (GDP)
  • Direct economic loss attributed to disasters in relation to global gross domestic product
  • (a) Number of commercial bank branches per 100,000 adults and (b) number of automated teller machines (ATMs) per 100,000 adults

示例地理范围

  • 西欧:152 个六边形网格
  • 过去半小时降雨率(IMERG),NASA GIBS
  • 今夜夜间灯光与停电(VIIRS 昼夜波段),NASA GIBS
  • 穿透云层的地表水,30 m(OPERA DSWx-S1 雷达),NASA GIBS
  • Carbon monoxide, smoke transport (AIRS), NASA GIBS
06来源

证据来自何处。

具名公共数据集与机构记录,各自注明许可类别。依协议获得的来源仅按其条款使用,绝不再次发布。

来源它提供什么许可类别
Actuarial Standards Board ASOP on credibility proceduresProfessional standards for credibility免费,ASB 条款
意外险精算学会(Casualty Actuarial Society)可信度专著Bühlmann and limited fluctuation methods免费阅读,适用 CAS 条款
Industry statistical agent dataPooled experience for benchmarks已许可,条款因代理而异
Structured expert judgement literature (Cooke method)Methods for eliciting and combining expert estimates可免费阅读,条款依出版方而定
Stan and PyMC documentationOpen-source Bayesian modelling tools开源、BSD 和 Apache 许可
07风险暴露、损失与资本

What credibility and sparse data means for exposure, loss and capital.

风险官、监管者或财政部会要求的风险暴露、损失、情景和资本视图,以及它们据以报告的框架。结构遵循监管和精算实务。数值为说明性:绝非价格、评级或建议。

各重现期的风险暴露与损失

How losses from credibility and sparse data grow with severity, gross and net of reinsurance, against capital.

1/10(10 年一遇)1/50(50 年一遇)1/100(100 年一遇)1/250(250 年一遇)总额扣除再保险后的净额800
重现期年概率总损失净损失净额,资本 = 100
1/10(10 年一遇)0.10141010
1/50(50 年一遇)0.02332121
1/100(100 年一遇)0.01462727
1/250(250 年一遇)0.004683939
年均损失3.12.22.2
一个示例投资组合的示意性损失指数(资本 = 100):保险公司和监管机构所读的超越概率形式。并非任何机构的数据,也非价格或评级。
NGFS 气候情景 · 央行与监管机构绿色金融网络IFRS S2 气候相关披露 · ISSBTCFD 建议 · 金融稳定理事会 TCFD有效管理气候相关金融风险的原则 · 巴塞尔银行监管委员会
08决定

由谁决定,以及证据服务于什么。

精算与定量风险负责准备证据。以下决定由所指定的主管机构依其自身规则作出,绝不由平台作出。

谁来决定问题本页面服务的证据
定价与准备金精算师对自有数据给予多大可信度,以及使用哪种基准风险暴露、基准相关性和专业标准
Product committeesWhether to launch products with sparse data and what monitoring applies不确定性估计和监测计划
监管机构针对新建或小型投资组合的假设是否合理Actuarial reports
再保险人如何为历史数据很少的投资组合定价承保Benchmarks and exposure data

该主题产生的产出

09核心问题

专家提出的问题。

  • How much weight should a portfolio’s own experience receive relative to wider data?
  • 哪些外部数据相关,目标人群的差异有多大?
  • How should expert judgement be elicited and combined with data?
  • How should the extra uncertainty from sparse data be reflected in results?
  • 面向数据匮乏情境的模型如何避免简单照搬数据丰富情境下的假设?
10机制

Credibility and borrowing strength.

Credibility theory, developed by actuaries over many decades, blends a risk’s own experience with a broader collective estimate, giving more weight to own experience as its volume and stability grow. The Bühlmann and Bühlmann-Straub models formalise this as a linear estimate that minimises expected error, and they are closely related to Bayesian methods and to hierarchical models in statistics.

Hierarchical Bayesian models extend the idea, letting groups such as regions, industries or policy types share information while retaining their own parameters. They make uncertainty explicit and can incorporate prior knowledge from expert judgement or related data. Structured expert elicitation methods help reduce bias when experts supply estimates.

In emerging risks such as cyber, the problem is not only volume but change: the threat environment evolves faster than data accumulate, so old data may be less relevant. In lower-income markets, using models built for other countries can embed assumptions about building quality, health or behaviour that do not hold.

11方法与数据

方法及其局限。

Credibility

Credibility models

Blending own and collective experience; requires a sensible definition of the collective.

Bayesian

层次模型

在各组之间共享信息并明确不确定性;结果取决于先验。

专家

Structured elicitation

获取并校准专家判断的正式方法。

局限:任何方法都无法凭空创造不存在的信息。稀疏数据的估计带有较大的不确定性,结果可能主要由对群体或先验的假设所左右。

12方法

如何研究,以及方法无法说明的内容。

13问题

问题与解答。

What is credibility in actuarial work?
The weight given to a portfolio’s own experience when combining it with broader data, increasing as the volume and stability of own data grow.
什么是 Bühlmann 可信度?
A method that sets credibility weights from the variance within and between risk groups, balancing own experience against the collective.
何时适合采用专家判断?
在数据缺失或不相关时适用,前提是以结构化、有记录的方式征询,并在数据到来时加以检验。
行业能否共享数据以缓解数据稀疏问题?
Only aggregated, under GRA’s written competition policy, once membership opens. Competitively sensitive data are not exchanged.
Is expert judgement scientific?
It can be, when elicited with structured methods, calibrated and documented, and when its uncertainty is reported.
为什么网络风险难以建模?
Because data are short, threats change quickly and losses can be highly correlated across firms.
报告贡献

从本页贡献证据。

Reports 是联合体的季刊。您对该主题的了解可以成为下一期中的证据、案例或更正,署名归您,并在属于您本人作品时以 CC BY 4.0 发布。

全球风险联盟(Global Risks Alliance)精算与量化风险方法与技术金融与保险准备度
精算与量化风险

向联盟提出风险暴露或资本问题。

信息和咨询现已开放。每项咨询都会获得一个编号,并告知下一步;申请、付款、算力分配和注册只有在相应团队、条款和审查能力就绪时才会开放。