Input data and information sources
The applicant supplies income, occupation and other application details. The system assesses a specific person using name, address and past payment behaviour.
Credit scoring and creditworthiness assessment
A model estimates repayment likelihood from payment and customer data, helping determine whether a person receives credit and on what terms.
Understand the use case
What defines this use case?
Banks and credit reference agencies use these scores. BaFin states that smaller institutions have so far rarely used AI for this purpose.
This page describes a typical system design. Actual data flows and permissions depend on your implementation.
- System design
- Analysis and processing
- Ability to act
- Action permissions depend on integration
- Fields of use
- banking, credit reference agencies
- Also known as
- scoring, creditworthiness checks, credit rating
How it works, step by step
System design and data flows
Input data
The model receives application details, account data and past payment information.
The applicant supplies income, occupation and other application details. The system assesses a specific person using name, address and past payment behaviour.
Processing
The model weights the information and calculates a default probability.
The model uses permitted information to assess creditworthiness or default risk. This assessment is combined with the credit process's decision rules. A score, a recommendation for a decision and a final lending decision are different outputs.
Results
The model returns a score or derived risk class.
The result describes the defined model task. A match, category or forecast acquires its professional significance only in conjunction with the underlying data and intended use.
Use and impact
The score helps determine whether credit is granted, its amount and interest rate.
Integration determines whether the result is simply displayed, adopted after approval or written directly into a business application. These variants differ in their data flows and permissions.
Explore the system design: Select a component to see its task, incoming and outgoing data, and role in the use case. The guided walkthrough explains each phase. Then use Yes, Uncertain and No to represent your specific system variant.
9 review first9 clarify6 baseline threats
- Present
- Depends on your system
- Absent
- Review first
- To clarify
How to use the model
The diagram shows the typical architecture. Select a component to see what happens there and adapt its features to your system. Enable “Analysis guidance” to see which threats need reviewing for this architecture. The page's checklist continues to describe the typical case.
Changes from the typical case
None yet. Each change will appear here.
Where most threats arise
- 4 review first
- 4 clarify
- 3 review first
- 1 review first, 1 clarify
In this system design: 9 to review first, 9 to clarify, 6 baseline threats.
Architecture as a list
External access: Depends on your system
To clarify
Input: Part of every AI system
Review first
Third-party content: Present
AI model: Part of every AI system
Review first
- Model Drift & Degradation Review priority
To clarify
Provider service: Depends on your system
To clarify
Training and feedback: Present
Review first
Result: Part of every AI system
Baseline for every AI system
Business application or equipment: Depends on your system
To clarify
person: Part of every AI system
Review first
- Overreliance Review priority
Affected person: Present
Unapproved AI services: Depends on your system
To clarify
Supply chain and technical foundations: 5 baseline threats applying to every AI system
Baseline for every AI system
How it differs from similar use cases
Assesses individual payments for fraud rather than a person's ability to repay
Life and health insurance risk assessment and pricing
Estimates mortality or illness risk to determine acceptance and premiums
Automated property valuation (AVM)
Estimates the value of property used as loan collateral
Data and information
Processing and operating environment
A bank using a credit reference agency's score relies on another provider's model.
Storage and further use
Banks and credit reference agencies develop scoring models from their own lending and payment data. Repayment of granted loans feeds into the next model version.
Results and data sharing
Depending on the credit process, the score triggers approval or rejection automatically or is only presented to caseworkers.
Using a provider does not automatically determine where processing takes place. Storage location, subcontractors, deletion periods and use for training must be checked for the specific deployment.
Assess risks and determine measures
From understanding the system to analysing risks
- Define the system boundary
Record data, participants, interfaces and permissions. Resolve uncertain characteristics in the model.
- Investigate threats
Relate review candidates to actual data flows: what could happen, and who would be affected?
- Assess risk
Assess impacts and likelihood in the deployment context. The number of review candidates is not a risk score.
- Provide evidence of measures
Select appropriate controls, assign responsibilities and define effectiveness checks. Document residual risks and approvals.
Key threats in the application context
- 4 particularly important
- 5 typical
- 9 depending on the system
- 6 additional threats for every AI system
A total of 24 threats from the threat catalogue may be relevant to this use case.
Also review: whether the system disadvantages groups
Check whether selection, ranking or assessment disadvantages people with protected characteristics, such as sex, age or origin.
Priority review points
A caseworker may reject a score just below the threshold without considering the person's situation. An estimate becomes a decision, even if the score is wrong.
The model knows earlier years' payment behaviour. Changing interest rates, labour markets or customers make default estimates too high or too low, without immediate detection.
Targeted Poisoning / Label Poisoning
The model learns from loans labelled repaid or defaulted. Incorrect or manipulated labels shift the approval boundary for all future applications.
Someone who knows which details improve the score can tailor an application to just exceed the threshold. The system recommends credit it would have rejected with accurate information.
5 further review candidates in the typical design
Other relevant threats
Your own training or operational feedback can introduce manipulated data into training datasets.
Listed because of these characteristics
- Learns from your own data
- Uses operational feedback
Training data or an adopted base model can introduce hidden triggers for misbehaviour.
Listed because of this characteristic
- Learns from your own data
Targeted queries can recover some personal or protected training data from the model.
Listed because of these characteristics
- Processes personal data
- Processes confidential data
Sensitive Information Disclosure
Confidential content can appear in answers, supplied context or logs.
Listed because of these characteristics
- Processes personal data
- Processes confidential data
Exfiltration from ML Application
Protected data can leak through tools, network connections, storage or insiders.
Listed because of this characteristic
- Processes confidential data
Up to 9 further threats may apply, depending on your system design. Nine threats need to be reviewed for every AI system. Three of these are particularly important here and are therefore listed above.
System features and open questions
Each Yes adds further threats to your checklist, up to 9 in total. If you cannot yet answer a question, include its threats in your review.
- Added by this Yes
How your system is built
- Changes data or triggers processes1 threat
- Optimises a specified metric1 threat
How you operate the system
How your system is built
Can the system change things itself, such as storing data, sending messages, initiating transactions or granting permissions?
Depending on the credit process, the score triggers approval or rejection automatically or is only presented to caseworkers.
If yes, add
Is the system intended to maximise a specified metric, such as revenue, utilisation or clicks?
A lender setting thresholds by approval rate or return directs the system towards a business objective.
If yes, add
How you operate the system
These questions arise for almost every AI system.
Can people or programs query the model directly, for example through an interface?
Credit reference agencies and platforms often provide scores through an interface.
If yes, add
Is the system accessible over a network or dependent on network services?
If yes, add
Do you pay per query or unit of computing time, so costs increase with use?
If yes, add
Does the system share servers or computing resources with other customers or applications?
If yes, add
Can people outside your organisation use the system, including without login?
Every person completing an online loan application triggers an assessment.
If yes, add
Do staff also use AI services for this task that your organisation has not approved?
If yes, add
Controls and implementation
Measures for the priority review areas are expanded. Each linked measure explains how to implement it.
Review priorityOverreliance3 measures
Review priorityModel Drift & Degradation3 measures
Review priorityTargeted Poisoning / Label Poisoning3 measures
Review priorityAdversarial Inputs2 measures
Training Data Poisoning2 measures
Backdoor ML Model2 measures
Privacy Attacks3 measures
Sensitive Information Disclosure3 measures
Exfiltration from ML Application3 measures
Controls for the remaining threats are available on their pages in the threat catalogue.
AI Act provisions
-
Art. 4: AI literacy
For every AI system Applies since 2 February 2025.
-
Annex III no. 5 point b: Creditworthiness
In typical use Review trigger from 2 December 2027.
Applies to every AI system
Art. 4: AI literacy
Applies if staff or appointed representatives operate or use AI systems.
Applies since 2 February 2025.
Obligations and details for Art. 4: AI literacy
- Who bears the obligations
- Provider, Deployer, Product manufacturer, Provider of a general-purpose AI model
Detailed obligations
May apply in typical use
Annex III no. 5 point b: Creditworthiness
Applies if the system assesses a natural person's creditworthiness or calculates their score, for example for consumer credit or instalment purchases.
Applies from 2 December 2027.
Obligations and details for Annex III no. 5 point b: Creditworthiness
- The general condition is
- Applies if the system assesses people's creditworthiness or establishes their credit scores.
- Exception
- Systems intended to detect financial fraud.
- Who bears the obligations
- Provider, Deployer, Product manufacturer
Detailed obligations
Other legal requirements
Article 22 GDPR
Calculating a score is itself an automated individual decision where the lender relies strongly on it (CJEU, C-634/21).
Classify your system with the quick checker All obligations in the obligations compass
Cross-cutting threats
Review these threats for every AI system, whatever its purpose.
- Supply Chain: Infrastructure
- Supply Chain: Models
- Supply Chain: Datasets
- Adversarial Inputs Review priority: Adversarial Inputs
- Insecure Output Handling
- Application Vulnerabilities
- Overreliance Review priority: Overreliance
- Model Drift & Degradation Review priority: Model Drift & Degradation
- Middleware Exploits (AI Framework Attacks)
Atypical system features
View 16 further questions
If any of these features does apply to your system, add the listed threats.
Does the system generate its own text, such as answers, drafts or summaries?
The system produces a score or risk class rather than text.
If yes, add
Does the system generate or edit images, sounds, voices or videos?
If yes, add
Does the system create new content from open-ended requests that people read, see or hear directly? Translation, reading aloud and transcription do not count.
If yes, add
Can users give the system natural language tasks that it then performs?
A scoring model uses application data and does not accept natural language instructions.
If yes, add
Does the system search its own collection of documents or records for relevant content?
If yes, add
Does the system formulate answers from retrieved documents?
If yes, add
Does the system use a knowledge graph storing concepts and their relationships?
If yes, add
Does the system remember content from earlier conversations or tasks and reuse it later?
If yes, add
Does the system call other programs, interfaces or search services itself, even if only to read?
If yes, add
Does the system determine its next steps itself based on earlier results?
If yes, add
Does the system delegate tasks to other AI agents or incorporate their results?
If yes, add
Is the system connected to tools or data sources through the Model Context Protocol (MCP)?
If yes, add
Do documents from several customers, departments or permission groups share one search store?
If yes, add
Does the system process several input types together, such as text with images or speech?
If yes, add
Does the system generate code, scripts or database queries for further use?
If yes, add
Does the system execute programs, scripts or commands itself?
If yes, add
Sources
- Legislation, norm or standard
EU AI Act, Annex III, point 5(b)
The Act expressly lists AI systems assessing natural persons' creditworthiness or establishing their credit scores in Annex III.
- Authority, court or parliament
Court of Justice of the EU, Press release No 186/23 on C-634/21 (SCHUFA)
The Court treats score calculation itself as automated individual decision-making under Article 22 GDPR where a third party relies strongly on it.
- Authority, court or parliament
EBA, Follow-up report on machine learning for IRB models, 2023
The European Banking Authority reports that banks primarily use machine learning to assess creditworthiness and calculate scores.
- Authority, court or parliament
BaFin, Article on AI in banks and insurers, 1 August 2024
BaFin warns that biased training data can lead to discrimination.
- Specialist study
OECD, Framework for the Classification of AI Systems, 2022
The OECD uses credit scoring as the first example in its AI classification framework.
- Authority, court or parliament
CFPB, CFPB Announces First No-Action Letter to Upstart Network, 14 September 2017
The agency identifies a provider assessing loan applications with an automated machine learning model.
- Authority, court or parliament
BaFin states that smaller institutions have so far rarely used AI to assess creditworthiness.
Related use cases
Also in the field of Banking and insurance
- Payment fraud detectionA model assesses each payment for suspected fraud in real time and stops suspicious payments or refers them for review.
- Money laundering detection and sanctions screeningBanks search account and payment data for money laundering patterns and check all parties against sanctions lists.
- Life and health insurance risk assessment and pricingInsurers estimate an applicant's mortality or illness risk to determine whether to accept them and what premium to charge.
- AI-assisted insurance claims handlingThe system analyses claim documents and photographs, checks entitlement against the policy, flags inconsistencies and prepares settlement.
Often used together with
Updated: 30 September 2026. Review checklist rules version 0.3.2, threat catalogue version 2026.10.24.2. How these pages are structured