Exposure enrichment from imagery
Models extract roof type, building footprint and vegetation proximity from aerial and satellite imagery to fill gaps in exposure data, with accuracy measured against inspected properties.
GRA · Insurance Nexus
空间金融资本与危害、风险暴露和转型的交汇之处
Artificial intelligence and machine learning are used in insurance to read images and documents, detect fraud, triage claims, enrich exposure data and segment risk. On this platform they are treated both as methods and as a source of risk to be governed, tested and explained.
Artificial intelligence and machine learning develop algorithms that learn patterns from data to classify, predict or generate outputs. They are increasingly used for hazard detection, forecasting and decision support, and are themselves a source of risk. In insurance and catastrophe, climate and hazards and health and biosecurity, machine learning can scale detection and forecasting across interconnected 系统. Its own failure modes must be weighed when automated outputs inform consequential decisions. The canonical description is on STEM Commons.
Models extract roof type, building footprint and vegetation proximity from aerial and satellite imagery to fill gaps in exposure data, with accuracy measured against inspected properties.
Classifiers score claims for complexity or fraud indicators to route them for review, with false positive rates, appeal outcomes and group disparities monitored beside detection.
Pricing and underwriting models are tested for disparate outcomes and proxy effects across groups, and less discriminatory alternatives are compared for predictive performance.
处于覆盖范围内的投资组合每年预期损失,以及保险公司和贷款机构定价所依据的 1/100 和 1/250 水平下的预期损失,均来自每个 巨灾模型 所用的同样三个模块。教学模型,所用数值为注明的示意值,并非预测。
控制措施
读数
| 重现期(年) | 强度(强度指数) | 损失(占价值的 %) |
|---|---|---|
| 1 | 0.09 | 0.00 |
| 2 | 1.27 | 0.00 |
| 4 | 1.91 | 0.00 |
| 7 | 2.47 | 0.00 |
| 13 | 3.00 | 0.00 |
| 24 | 3.51 | 0.00 |
| 44 | 4.02 | 0.00 |
| 82 | 4.53 | 23.55 |
| 154 | 5.03 | 26.44 |
| 287 | 5.53 | 28.87 |
| 536 | 6.03 | 30.88 |
| 1,000 | 6.53 | 32.53 |
The model runs on the teaching values set by the controls. To calibrate it for a place, read it against these admitted layers and series, which this page’s map can draw:
贯穿六大支柱,由 Nexus Consortium 牵头
| 数据 | 角色 | 标签 |
|---|---|---|
| Aerial and satellite imagery | Exposure attributes | 观测 |
| Labelled claims histories | Training and testing | 已报告 |
| Property inspection records | Ground truth for imagery models | 观测 |
| Demographic reference data | Fairness testing | 估算 |
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。
How losses from machine learning in insurance grow with severity, gross and net of reinsurance, against capital.
| 重现期 | 年概率 | 总损失 | 净损失 | 净额,资本 = 100 |
|---|---|---|---|---|
| 1/10(10 年一遇) | 0.10 | 14 | 10 | 10 |
| 1/50(50 年一遇) | 0.02 | 33 | 21 | 21 |
| 1/100(100 年一遇) | 0.01 | 46 | 27 | 27 |
| 1/250(250 年一遇) | 0.004 | 68 | 39 | 39 |
| 年均损失 | 3.1 | 2.2 | 2.2 |
模型在尊重空间、时间与群体结构的留出数据上进行评估。在测试准确性的同时,也测试稳健性、校准与公平性。
| 核查 | 如何开展 |
|---|---|
| Temporal and held-out validation | Models are tested on later periods and unseen regions, not only on random splits |
| Calibration and drift monitoring | Predicted probabilities are compared with outcomes over time, and drift triggers recalibration |
| Fairness and explainability review | Outcome disparities and explanations are reviewed before deployment and periodically after |
| 人工监督 | Decisions adverse to customers have a documented human review and an appeal route |
当部署条件与训练数据不同时,性能会下降。模型可能固化偏见,并在罕见事件上毫无明显预警地失效。
报告 is the Consortium’s quarterly publication. What you know about this subject can become evidence, a case or a correction in the next edition, credited to you and published under CC BY 4.0 where it is your own work.
切勿发送个人数据、敏感基础设施细节或您无权分享的任何内容。贡献在使用前会经过审查;发送贡献不赋予署名权或编辑权,赞助也绝不能换取研究结论。
本网站上的地图、数据和图表仅作为背景和一般信息展示。它们不是建议、预测或预警;信息的局限见免责声明和数据说明。
This site uses only strictly necessary cookies to work and to remember your privacy choices. Nothing loads from other companies, and we never sell or share your personal information.
This site uses only strictly necessary cookies to work and to remember your privacy choices. Nothing loads from other companies, and we never sell or share your personal information. We run no advertising. You can review your choices at any time through Privacy choices at the foot of every page.