Skip to content

GRA · Banking Nexus

Spatial financeWhere capital meets hazard, exposure and transition

Machine learning in banking

Artificial intelligence and machine learning now support credit underwriting, fraud and financial crime detection, early warning of borrower stress and supervisory analysis. In banking they are both a tool and a source of risk: their outputs must be explainable, fair, robust and validated before they influence consequential decisions about customers or capital.

02અરજી

What artificial intelligence and machine learning does here.

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 financial stability, capital markets and investment and climate and hazards, 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.

Credit decisioning with explainability

Gradient boosting and similar models are developed alongside interpretable scorecards; explanations of individual decisions are produced and tested for stability before any use in lending.

Early warning and transaction monitoring

Transaction and account data are used to flag borrowers showing early signs of distress and patterns associated with fraud, with every alert reviewed by a person.

Text analysis for risk and supervision

Language models and text classifiers extract risk signals from filings, incident reports and supervisory documents, with outputs checked against human review.

03દેખરેખ

Model training.

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

Model training

Banking · Machine learning in banking · Run R-5640

Drift on one sliceGRA · Banking Nexus

Evaluation by slice

All0.890.055695Pass
Region A0.850.061734સમીક્ષા
Region B0.680.09636સમીક્ષા
Rare class0.710.11144Below bar

Method card

પદ્ધતિ
કૃત્રિમ બુદ્ધિ અને મશીન લર્નિંગ
Split
time-based, no leakage
Features
56
લેબલ
મોડેલ આધારિત

Population stability

Model training: the screen’s structure, terms and states for Banking.Example names and illustrative values; a design, not a record or a live system.
04ડેટા

What the method consumes.

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.

ડેટાભૂમિકાલેબલ
Credit application and performance dataTraining and validationઅવલોકિત
Transaction recordsMonitoring and early warning featuresઅવલોકિત
Public filings and supervisory publicationsText corporaPublished statistics
Cash-flow and alternative data used under consent and lawAdditional borrower featuresનોંધાયેલ
05Stress test

How a shock to assets becomes a system loss.

The equity the system loses after interbank contagion, against the initial hit, as leverage, interconnection and recovery rates change, the core of a macroprudential stress test. Teaching model with stated illustrative values, not a prediction.

નિયંત્રણો

Fall in external assets
2.0%
Leverage (assets over equity)
10 times
Interbank share of assets
10%
Recovery on interbank claims
40%
Banks in the system
20
Core banks
20% of banks

વાચનો

Equity lost to the initial shock
18.0%
Equity lost after contagion
45.0%
Added by contagion (DebtRank)
27.0 points
Banks in default
0
આંકડા, પદ્ધતિઓ અને સ્ત્રોતો
RoundSystem equity lost (%)Banks in default
018.000
128.800
235.280
339.170
441.500
542.900
643.740
744.240
844.550
944.730
1044.840
1144.900
1244.940
1344.960
1444.980
1544.990
1644.990
1745.000
1845.000
1945.000
2045.000
2145.000
2245.000
2345.000
2445.000
2545.000
2645.000
2745.000
2845.000
2945.000
3045.000

પદ્ધતિઓ

  1. DebtRank Battiston and others (2012), Scientific Reports 2:541
  2. Differential DebtRank Bardoscia and others (2015), PLOS ONE 10
  3. Contagion in financial networks Gai and Kapadia (2010), Proc. R. Soc. A 466
  4. Clearing in financial networks Eisenberg and Noe (2001), Management Science 47
  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

ડેટા

No observed data enters this model: it runs on the teaching values set by the controls, to be replaced with a programme’s own evidence.

How a shock to assets becomes a system loss. Illustrative teaching model: it runs on the values set by the controls, not on measured data. Methods: DebtRank (Battiston and others (2012), Scientific Reports 2:541); Differential DebtRank (Bardoscia and others (2015), PLOS ONE 10); Contagion in financial networks (Gai and Kapadia (2010), Proc. R. Soc. A 466).

છ સ્તંભોમાં, Nexus Consortium ના નેતૃત્વ હેઠળ

06માન્યતા

How results are checked.

Models are evaluated on held-out data that respects spatial, temporal and group structure. Robustness, calibration and fairness are tested alongside accuracy.

CheckHow it is done
Temporal hold-outModels are evaluated on periods later than the training data, never on random splits alone
Fairness testingOutcomes are compared across groups using several fairness definitions, and the trade-offs are reported
Explanation stabilityExplanations are checked for consistency across similar cases and over time
Drift monitoringInput and output distributions are tracked against thresholds that trigger review and retraining

Performance degrades when deployment conditions differ from training data. Models can encode biases and fail without clear warning on rare events.

07Exposure, loss and capital

What machine learning in banking 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.

Scenario pathways

How machine learning in banking could be stressed under the scenario families central banks and supervisors use.

OrderlyDisorderlyHot house world202520302035204020452050highlow
Scenario familyTransition riskPhysical riskWhat a stress test asks
OrderlyEarly, gradual policyLowerCan the book absorb a steady repricing?
DisorderlyLate, abrupt policyLower to mediumWhat breaks under a sudden repricing and credit migration?
Hot house worldLimited policyHigh and risingWhere do physical losses concentrate in collateral and insurance?
Scenario families as defined by the NGFS; the curves are an illustrative combined pressure index, not NGFS variables or forecasts.
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
09સંરક્ષકતા

Who maintains the method.

Artificial Intelligence and Autonomous Systems stewards artificial intelligence and machine learning for the Consortium and reviews how it is applied across platforms.

10જોડાયેલ

સમગ્ર કન્સોર્ટિયમમાં આ પૃષ્ઠ ક્યાં લઈ જાય છે.

11પ્રશ્નો

પ્રશ્નો અને જવાબો.

What are the limits of artificial intelligence and machine learning in this field?
Performance degrades when deployment conditions differ from training data. Models can encode biases and fail without clear warning on rare events.
How are results checked?
Models are evaluated on held-out data that respects spatial, temporal and group structure. Robustness, calibration and fairness are tested alongside accuracy.
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.
અહેવાલોયોગદાન આપો

આ પૃષ્ઠ પરથી પુરાવાનું યોગદાન આપો.

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 AllianceBanking NexusFinance and Insurance ReadinessScenario and Stress-Test

ક્યારેય વ્યક્તિગત ડેટા, સંવેદનશીલ માળખાકીય સુવિધાઓની વિગતો અથવા તમને શેર કરવાનો અધિકાર ન હોય તેવું કંઈપણ મોકલશો નહીં. ઉપયોગ પહેલાં દરેક યોગદાનની સમીક્ષા થાય છે; તે મોકલવાથી કોઈ લેખકત્વ અથવા સંપાદકીય અધિકારો મળતા નથી, અને પ્રાયોજકતા ક્યારેય કોઈ તારણ ખરીદી શકતી નથી.

બેંકિંગ Nexus

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.

કાનૂની

આ સાઇટ પરના નકશા, ડેટા અને આકૃતિઓ સંદર્ભ અને સામાન્ય માહિતી માટે દર્શાવવામાં આવ્યા છે. તે સલાહ, આગાહી અથવા ચેતવણી નથી; માહિતીની મર્યાદાઓ અસ્વીકરણો અને ડેટા સૂચનાઓમાં દર્શાવેલી છે.