A-P08 · EVIDENCE · methodsGRA dossier · service level R0
GRAFinancial Crime and Fraud RiskIn development
Methods and uncertainty

Analysis and uncertainty

The methods Financial Crime and Fraud Risk relies on, the assumptions they carry and the limits of what they can show.

Make an enquiry Back to Professional research
Publisher
The Global Risks Alliance
Field
Financial stability, Cyber and digital resilience, Governance and institutions
Status
In development
Service level
R0: information and enquiries

Evidence register

Financial crime · Analysis and uncertainty

Register currentGRA · Financial Crime and Fraud Risk

Indicators

unit · cadence · label

Alerts generatedalerts / daydailyOBSERVEDSP-9777
Alerts escalated to cases of alertsweeklyOBSERVEDSP-7761
Suspicious activity reports filedreportsmonthlyOFFICIALSP-7742
Mean age of open casesdaysweeklyOBSERVEDSP-5284
Sanctions screening hit rateper 1,000 screensdailyOBSERVEDSP-4479

Source passport

Source
Transaction monitoring alerts
Licence
open · attribution
Steward
Financial intelligence unit liaison
Coverage
81 pct of places
Known limits
sparse in uplands

Coverage by place

Financial Crime and Fraud Risk · Evidence registerEvidence register, in outline: domain structure with placeholder names and illustrative values, not a record.

01In brief

The short answer.

The Financial Crime and Fraud Risk methods page sets out the methods the platform relies on, among them artificial intelligence and machine learning, network science and contagion, and data engineering, interoperability and stewardship, with their assumptions, validation and limits. Each analysis lists its assumptions and data, reports ranges and confidence beside central estimates, is checked against observations or other models, and states what it cannot show.

02Canvas

Draft to published version.

Canvas · draft to published versionDesign, not a record
Analysis and uncertainty: systematic evidence synthesisA question is framed with its owner and a protocol registered; records are searched, screened and checked for eligibility by two reviewers; data are extracted, synthesised and graded for certainty before a brief is written. Design of the process, not a record of a run.

Fig.How a finding is reviewed before it is published. Design, not a record.

03Geography

Activity and exposure in Mexico.

Night-time lights and population, a proxy for economic activity, with the floods and fires that put assets at risk, framed on Mexico; each layer is a dated NASA product.

The interactive map needs JavaScript; the layer list and sources are below.

Layers 2

Activity and exposure

Latest available

NASA GIBS / EOSDIS · ASTER GDEM (METI, NASA) · Natural Earth

Loading the latest NASA imagery.

Drag to move. Ctrl or ⌘ and scroll, pinch or the buttons to zoom; hover for the values under the pointer; reset returns to the region.

Night-time lights and population, a proxy for economic activity, with the floods and fires that put assets at risk, framed on Mexico.Satellite and model products as NASA publishes them, each with its own date; indicators, not assessments of any place; claim ceiling INTEGRATED.

Data: NASA GIBS · ASTER GDEM · Natural EarthSources and licences

  • We acknowledge the use of imagery provided by services from NASA's Global Imagery Browse Services (GIBS), part of NASA's Earth Science Data and Information System (ESDIS). Colours redrawn from the published colour map; values averaged into H3 cells where shown (modified). NASA open data
  • We acknowledge the use of imagery provided by services from NASA's Global Imagery Browse Services (GIBS), part of NASA's Earth Science Data and Information System (ESDIS). Colours redrawn from the published colour map; values averaged into H3 cells where shown (modified). NASA open data
  • VIIRS Black Marble night-time lights, NASA Goddard Space Flight Center; distributed by the NASA Level-1 and Atmosphere Archive and Distribution System (LAADS DAAC); imagery via NASA GIBS. Colours redrawn from the published colour map; values averaged into H3 cells where shown (modified). NASA open data
  • Center for International Earth Science Information Network (CIESIN), Columbia University. 2018. Gridded Population of the World, Version 4 (GPWv4): Population Density, Revision 11. NASA Socioeconomic Data and Applications Center (SEDAC). Licensed under CC BY 4.0. Colours redrawn from the published colour map; values averaged into H3 cells where shown (modified). CC BY 4.0
  • VIIRS near-real-time products (flood, land surface temperature, snow cover, corrected reflectance), NASA LANCE; imagery via NASA GIBS. Colours redrawn from the published colour map; values averaged into H3 cells where shown (modified). NASA open data
  • NASA Fire Information for Resource Management System (FIRMS), VIIRS 375 m active fire product, NASA LANCE; vector tiles via NASA GIBS. Colours redrawn from the published colour map; values averaged into H3 cells where shown (modified). NASA open data
  • ASTER GDEM is a product of METI and NASA (ASTER Global Digital Elevation Model V003, NASA LP DAAC); imagery via NASA GIBS. Colours redrawn from the published colour map; values averaged into H3 cells where shown (modified). NASA open data
  • Made with Natural Earth. Free vector and raster map data @ naturalearthdata.com. Public domain
  • Globe: MapLibre GL JS 6.9.1, BSD-3-Clause, © MapLibre contributors.

Layers and dates

  • Night-time lights, daily: VIIRS Black Marble (VNP46A2), NASA LAADS DAAC · 12 Oct 2026
  • Population density, 2020: Population: CIESIN, Columbia University, Gridded Population of the World v4.11 (2018), NASA SEDAC, CC BY 4.0 · static
  • Flood water, 3-day composite: VIIRS Global Flood Product, NASA LANCE · 14 Oct 2026
  • Active fires and thermal anomalies, last day: VIIRS NOAA-20 375 m (FIRMS), NASA LANCE FIRMS · 13 Oct 2026
  • Land surface temperature, day, 8-day composite: VIIRS NOAA-20 Level 3, 8-day, NASA LANCE · 14 Sep 2026

04Methods

The methods in use.

  1. Artificial intelligence and machine learningReal-time fraud scoring · Alert prioritisation · Fairness in fraud controlsApplied here
    Canonical · STEM Commons
  2. Network science and contagionMule network detection · Ownership chain analysis · Cross-institution patternsApplied here
    Canonical · STEM Commons
  3. Data engineering, interoperability and stewardshipScreening data quality · Monitoring coverage checks · Retention and minimisationApplied here
    Canonical · STEM Commons
  4. Digital identity and public digital systemsAssurance levels for onboarding · Defending against deepfakes · Inclusion testingApplied here
    Canonical · STEM Commons
  5. Distributed ledgers and digital assetsBlockchain analytics · Travel rule implementation · Obfuscation techniquesApplied here
    Canonical · STEM Commons
05Methods

Detection methods and their trade-offs.

MethodStrengthWeakness
Rules and scenariosTransparent and auditableHigh false positives; easy to evade
Supervised learningLearns from confirmed casesLabel scarcity and delay
Anomaly detectionFinds new patternsMany anomalies are benign
Graph analyticsSees networks, not single accountsNeeds data across institutions
06Model risk

Detection models are models.

AML and fraud models fall under model risk management. In the United States the April 2026 revised guidance (SR 26-2) replaced both SR 11-7 and the 2021 interagency statement on BSA/AML model risk. Model governance at AI and Financial Model Risk.

07Uncertainty

How uncertainty is reported.

  1. 01

    State assumptions

    Each analysis lists its assumptions and the data it depends on.

  2. 02

    Quantify where possible

    Ranges and confidence are reported alongside central estimates.

  3. 03

    Validate and compare

    Models are checked against observations and, where possible, against other models.

  4. 04

    Publish limits

    What an analysis cannot show is stated beside what it can.

08Key terms

Terms used on this page.

Each term as this page uses it. Where a standard-setting body defines the term, the wording follows that body.

TermDefinition
Uncertainty quantificationCharacterising and propagating the uncertainties in a model to state confidence in its outputs.
Sensitivity analysisRepeating an analysis under different assumptions to show how much the result depends on them.
Model validationIndependent testing that a model performs as intended and is fit for a stated use.
Artificial intelligence and machine learningArtificial intelligence and machine learning develop algorithms that learn patterns from data to classify, predict or generate outputs.
09Sources

Where this page's references lead.

The bodies and documents this page is read against. Status and editions change; each link goes to the issuing body.

10Questions

Questions and answers.

Are the methods open?
Method descriptions are public on the STEM Commons. Code and data follow their own licences and access terms, listed in the source register.
Related

Around Financial Crime and Fraud Risk.

Financial Crime and Fraud Risk

Bring your expertise to this field.

The current service level is R0: information and enquiries. 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.

Write to the team See all contact routes
Skip to toolbar