Skip to content

GRA · Actuarial and Quantitative Risk

Spatial financeWhere capital meets hazard, exposure and transition

Extreme value theory and tail risk for actuarial and quantitative risk

Extreme value theory models the tails of loss and hazard distributions. On this platform it supports large-loss pricing, catastrophe hazard, operational risk and capital at high confidence levels, with threshold choice and uncertainty made explicit.

02Application

What extreme value theory and tail risk does here.

Extreme value theory and tail risk study the behaviour of rare, high-impact events. They provide methods to estimate the magnitude and frequency of extremes beyond the range of observed data. In insurance and catastrophe, methods and modelling and capital markets and investment, extreme value methods set design levels and capital buffers for rare events. Tail dependence analysis reveals when extremes in different systems tend to occur together. The canonical description is on the STEM Commons.

Excess layer pricing

Losses above a threshold are fitted with a generalised Pareto distribution to price excess-of-loss layers, showing how threshold choice moves the price.

Non-stationary hazard extremes

Covariates such as time or climate indices are added to extreme value models to test whether tails are changing over time.

03Spatial finance

Exposure, hazard and the exceedance curve.

Which places drive loss in a severe year, and how far it reaches into reinsurance. Illustrative design values.

Coastal exposure under cyclone and earthquake zones, beside the loss curve it produces.Illustrative design values, not a model output or a price.
04Data

What the method consumes.

Datasets and records used by extreme value theory and tail risk on this platform, with the role each plays and the label its values carry. Sources are listed in the source register.

DataRolLabel
Large-loss historiesTail fittingOBSERVED
Hazard maximaHazard tailsOBSERVED
Simulated event setsTail extensionMODELLED
05Monitor

Tail fit.

The screen a team would use to follow this method: its measures, states and decisions. Names are examples and values are illustrative.

Tail fit

Actuarial and quantitative risk · Extreme value theory and tail risk · Run R-3811

Shape parameter uncertainGRA · Actuarial and Quantitative Risk

Return level curve

Method card

Method
Ekstreemwaardeteorie en stertrisiko
Benadering
peaks over threshold
Threshold
96th percentile
Label
MODELLED

Parameters

generalised Pareto fit

Shape ξ0.18−0.020.45heavy tail if above zero
Scale σ2.10.96.0units of the variable
Exceedances123declustered
Tail fit: the screen’s structure, terms and states for Actuarial and quantitative risk.Example names and illustrative values; a design, not a record or a live system.
06Validation

How results are checked.

Fits are checked with diagnostic plots, goodness-of-fit tests and out-of-sample comparison. Sensitivity to threshold and record length is reported.

CheckHow it is done
Threshold stabilityParameters are checked across thresholds
Interval reportingConfidence intervals accompany return levels
Stationarity testsTrends are tested before stationary fits are used

Extrapolation far beyond the data is highly uncertain. Changing climates and markets violate stationarity assumptions.

07Loss model

Loss exceedance, average annual loss and probable maximum loss.

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. The map on this page shows Japan and Korea; the model itself is not tied to a place.

Controls

Typical annual hazard intensity (location)
1.00 intensity index
Spread of extremes (scale)
0.80 intensity index
Intensity at which half the value is lost
4.00 intensity index
Dispersion of vulnerability
0.55
Share of value in the hazard footprint
40%
Protection standard (return period)
50 years

Readouts

Average annual loss
0.51% of value
Loss at 1 in 100 years
24.5% of value
Loss at 1 in 250 years
28.4% of value
Intensity at 1 in 100 years
4.68 intensity index
Numbers, methods and sources
Return period (years)Intensity (intensity index)Loss (% of value)
10.090.00
21.270.00
41.910.00
72.470.00
133.000.00
243.510.00
444.020.00
824.5323.55
1545.0326.44
2875.5328.87
5366.0330.88
1,0006.5332.53

Metodes

  1. Gumbel extreme-value hazard Gumbel (1958), Statistics of Extremes, Columbia University Press
  2. Lognormal fragility (vulnerability) FEMA (2003), HAZUS-MH Technical Manual
  3. Exceedance-probability curve and average annual loss Grossi and Kunreuther (2005), Catastrophe Modeling, Springer
  4. Levee effect Di Baldassarre and others (2013), Socio-hydrology, HESS 17
  5. Uncertainty fan (parameter Monte Carlo) Spiegelhalter, Pearson and Short (2011), Visualising uncertainty about the future, Science 333
  6. One-at-a-time sensitivity (tornado) Saltelli and others (2008), Global Sensitivity Analysis: The Primer, Wiley

Data

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:

  • Rivers Natural Earth
  • Urban extents Natural Earth
  • Cities Natural Earth
  • Earthquakes M4.5+, past week (USGS) U.S. Geological Survey · register usgs.earthquake.summary-feeds
  • Rain rate, last half hour (IMERG) NASA GPM IMERG Early · register nasa.gibs.context-live-layers
  • River discharge forecast, 30 days with range (GloFAS via Open-Meteo) Open-Meteo.com (CC BY 4.0), Copernicus GloFAS · register open-meteo.public-pages
  • Built-up and settlement extent, 2010 (HBASE, Landsat) CIESIN/Columbia, NASA SEDAC HBASE · register sedac.context-urban-layers
Loss exceedance, average annual loss and probable maximum loss. Illustrative teaching model: it runs on the values set by the controls, not on measured data. Methods: Gumbel extreme-value hazard (Gumbel (1958), Statistics of Extremes, Columbia University Press); Lognormal fragility (vulnerability) (FEMA (2003), HAZUS-MH Technical Manual); Exceedance-probability curve and average annual loss (Grossi and Kunreuther (2005), Catastrophe Modeling, Springer).
09Twin and cascade simulator

Trace a shock 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.

Gevare

  • Tropical cyclone
  • Earthquake
  • Ice-jam flood
  • Veldbrand
  • Storm surge (set off downstream)
  • Intense rainfall (set off downstream)
  • River flood (set off downstream)
  • Flash flood (set off downstream)
  • Dangerous surf (set off downstream)
  • Widespread power outage (set off downstream)
  • Mass displacement (set off downstream)
  • Coastal flood (set off downstream)
  • 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)

Controls

  • NS-0 Grondwet en beginsels
  • NS-3 Risikorekord-UNI's (grammatika, oorerflike kruisverwysing, toewysingsgesag)
  • NS-9 Kontekstuele UNI's (ontplooiings, instansies, programinstansies)
  • NS-10 Policies and clauses (machine-readable obligations: definition, binding, evaluation and enforcement)
  • NS-11 Verifikasie en monitering (getuienis, attestasies, zero-trust-ooreenstemmingwaarneming)
  • NS-14 Konformiteit en ooreenkomstabel met eksterne standaarde
  • NRS-F3 Insurance, catastrophe risk and protection gaps
  • NRS-H113 Hazard family: Financial-system fragility (NHS-1 soc.financial-system)
  • NRS-U17 Universe platform profile: Insurance Nexus
  • NRS-H71 Hazard family: Deep-time and cosmic catastrophes (NHS-1 planet.deep-time)
  • NRS-H65 Hazard family: Planetary boundary transgressions (NHS-1 planet.boundary)
  • NRS-F8 Parametric and index-based risk transfer

Observation

  • 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

Example geography

  • Western Europe: 152 hexagonal cells
  • Rain rate, last half hour (IMERG), NASA GIBS
  • Night lights tonight, outages (VIIRS Day/Night Band), NASA GIBS
  • Surface water through cloud, 30 m (OPERA DSWx-S1 radar), NASA GIBS
  • Carbon monoxide, smoke transport (AIRS), NASA GIBS
10Stewardship

Who maintains the method.

Reinsurance and Catastrophe stewards extreme value theory and tail risk for the Consortium and reviews how it is applied across platforms.

11Exposure, loss and capital

What it means for exposure, loss and capital.

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.

Exposure and loss at return periods

How losses from extreme value theory and tail risk for actuarial and quantitative risk grow with severity, gross and net of reinsurance, against capital.

1 in 101 in 501 in 1001 in 250grossnet of reinsurance800
Return periodAnnual probabilityGross lossNet lossNet, capital = 100
1 in 100.10141010
1 in 500.02332121
1 in 1000.01462727
1 in 2500.004683939
Average annual loss3.12.22.2
Illustrative loss index for a example portfolio (capital = 100): the exceedance-probability form insurers and supervisors read. Not data on any institution, not a price or a rating.
NGFS climate scenarios · Network for Greening the Financial SystemIFRS S2 Climate-related Disclosures · ISSBTCFD recommendations · Financial Stability Board TCFDPrinciples for the effective management of climate-related financial risks · Basel Committee on Banking Supervision
13Vrae

Questions and answers.

What are the limits of extreme value theory and tail risk in this field?
Extrapolation far beyond the data is highly uncertain. Changing climates and markets violate stationarity assumptions.
How are results checked?
Fits are checked with diagnostic plots, goodness-of-fit tests and out-of-sample comparison. Sensitivity to threshold and record length is reported.
Are the values on this page real?
The data names, roles and checks are real descriptions of practice. The canvas shows a design of the method’s use, not a run; no result is reported here.
Where else is this method applied?
The canonical method page lists every platform that applies it.
VerslaeDra by

Dra bewyse vanaf hierdie bladsy by.

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.

Global Risks AllianceActuarial and Quantitative RiskMethods and TechnicalFinance and Insurance Readiness
Aktuariële en kwantitatiewe risiko

Bring an exposure or capital question to the Alliance.

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.