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
Spatial financeWhere capital meets hazard, exposure and transition
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 systems. Its own failure modes must be weighed when automated outputs inform consequential decisions. The canonical description is on the 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.
The loss a portfolio in the footprint can expect per year and at the 1 in 100 and 1 in 250 levels that insurers and lenders price, from the same three blocks every catastrophe model uses. Teaching model with stated illustrative values, not a prediction.
Izilawuli
Iziphumo ezifundwayo
| Return period (years) | Intensity (intensity index) | Loss (% of value) |
|---|---|---|
| 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:
Kwiintsika ezintandathu, kukhokelwa yi-Nexus Consortium
Datasets and records used by artificial intelligence and machine learning on this platform, with the role each plays and the label its values carry. Sources are listed in the source register.
| Idatha | Indima | Ileyibhile |
|---|---|---|
| Aerial and satellite imagery | Exposure attributes | KUQWALASELWE |
| Labelled claims histories | Training and testing | KUXELIWE |
| Property inspection records | Ground truth for imagery models | KUQWALASELWE |
| Demographic reference data | Fairness testing | KUQIKELELWE |
The exposure, loss, scenario and capital views a risk officer, supervisor or ministry of finance would ask for, with the frameworks they report against. Structures follow supervisory and actuarial practice. Values are illustrative: never prices, ratings or advice.
How losses from machine learning in insurance grow with severity, gross and net of reinsurance, against capital.
| Return period | Annual probability | Gross loss | Net loss | Net, capital = 100 |
|---|---|---|---|---|
| 1 in 10 | 0.10 | 14 | 10 | 10 |
| 1 in 50 | 0.02 | 33 | 21 | 21 |
| 1 in 100 | 0.01 | 46 | 27 | 27 |
| 1 in 250 | 0.004 | 68 | 39 | 39 |
| Ilahleko yonyaka ephakathi | 3.1 | 2.2 | 2.2 |
Models are evaluated on held-out data that respects spatial, temporal and group structure. Robustness, calibration and fairness are tested alongside accuracy.
| Check | How it is done |
|---|---|
| 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 |
| Human oversight | Decisions adverse to customers have a documented human review and an appeal route |
Performance degrades when deployment conditions differ from training data. Models can encode biases and fail without clear warning on rare events.
Artificial Intelligence and Autonomous Systems stewards artificial intelligence and machine learning for the Consortium and reviews how it is applied across platforms.
Reports 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.
Musa ukuthumela idatha yobuqu, iinkcukacha ezibuthathaka zeziseko zophuhliso okanye nantoni na ongenalungelo lokwabelana ngayo. Umnikelo uphononongwa phambi kokuba usetyenziswe; ukuwuthumela akunikezi bubhali okanye amalungelo okuhlela, kwaye uxhaso alusoze luthenge isigqibo.
Information and enquiries are open today. An enquiry receives a reference and names the next step; applications, payments, compute allocations and registrations open only when their team, terms and review capacity exist.
Iimephu, idatha nemizobo ekule sayithi iboniswa njengemeko nolwazi jikelele. Ayingomacebiso, uqikelelo okanye izilumkiso; imida yolwazi ichazwe kwiZilumkiso neZaziso zeDatha.
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.