AI use case

AI drafted explanations for credit declines and adverse actions

An assistant that turns the reason codes of a credit model into an accurate, specific and readable explanation of a decline, reduced limit or repricing for the customer, and a matching internal rationale for the file, without adding any reason the model did not produce.

By Len Debets · Last verified 27 September 2026 · 2 public deployments

USD 66,667 to USD 400,000
Indicative value per year
A consumer lender issuing 100,000 adverse action notices a year. Worked example, see how it is calculated.

What problem does it solve?

When a lender declines an application, cuts a credit line or offers worse terms, it often has to tell the customer why: in the US, Regulation B requires the principal reasons for a decline or other adverse action, and EU law gives people a right to an explanation of automated credit assessments. In practice a notice can be little more than a list of checked reasons from a sample form ("limited credit experience", "excessive obligations in relation to income") that says little to the customer and may not reflect what really drove the decision. Complex machine learning models make this harder: a model can weigh many features, and the reasons printed must still be the principal ones and must be accurate.

The rules are explicit. In the US, Regulation B requires a statement of reasons that is specific and indicates the principal reasons, and says that checking the closest reason on a sample form is not enough when it is not the factor actually used. The CFPB's 2022 circular stating that this applies equally to complex algorithms was withdrawn in May 2025 together with many other CFPB guidance documents, but the adverse action notice requirements in 12 CFR 1002.9 and their official interpretation are unchanged. In the EU, the Court of Justice ruled in February 2025 (Dun & Bradstreet Austria) that a person subject to an automated credit assessment is entitled to an explanation of the procedure and principles actually applied, and the EU AI Act adds a right to an explanation for decisions based on high risk systems such as credit scoring. Vague or inaccurate explanations leave customers without a clear next step and the lender exposed on compliance.

How does it work?

  1. Take the decision record. The assistant receives the decision, the reason codes and their ranking from the decision engine, and the relevant customer and product data.
  2. Retrieve approved wording. For each reason code it retrieves the approved plain language description and, where allowed, what the customer could do about it.
  3. Draft within strict limits. A generative model composes the notice and a short internal rationale using only those reasons, in the customer's language and at an agreed reading level.
  4. Check automatically. A second pass verifies that every reason in the draft maps to a code from the decision, that no code is missing, and that no prohibited content appears.
  5. Review and send. A reviewer approves the draft, or approved templates go out automatically once quality is proven. Follow up questions go to an assistant limited to the same reasons, with a route to a person.
Audience
Employee facing
Autonomy
Copilot
Adoption
Emerging
Channels
Email, Mobile app, Web chat, Agent desktop

What is it worth?

Benchmarks are computed from the public deployments below: one data point per organization per KPI, with who made each claim.

No public deployment has disclosed a measurable outcome yet.

Value drivers: Compliance quality, Customer experience, Employee productivity.

Indicative value

A consumer lender issuing 100,000 adverse action notices a year

USD 66,667 to USD 400,000

Operations effort saved on decline follow ups per year

How this is calculated

Formula: notices * followUpShare * minutesSaved / 60 * hourlyCost. The low scenario uses every low input, the high scenario every high input.

InputLowHighBasis
Adverse action notices per year notices, notices per year100,000100,000The reference lender.
Share of notices that lead to a question, complaint or reconsideration request followUpShare, fraction of notices0.050.1Editorial assumption. Replace with your own contact and complaint data.
Minutes saved per follow up case with a clear explanation and a prepared rationale minutesSaved, minutes per case2040Editorial assumption for looking up the decision and writing a response. Replace with your own time study.
Fully loaded cost of a lending operations hour hourlyCost, USD per hour4060Editorial assumption.

What it leaves out: Counts handling effort only. The larger value, lower regulatory and fair lending risk and fewer repeat failed applications, is real but hard to price and is left out.

Who already uses it?

2 public deployments, strongest evidence first. Grades: A regulator or audit, B the organization itself, C vendor case study, D anonymous or estimate.

Discover Financial Services

United States · Banking · 2024

AnnouncedGrade B

Discover Financial Services patented a framework that generates the adverse action reason codes a lender must give a declined credit applicant directly from a machine learning model. The system groups correlated input variables, scores each group with partial dependence plots and Shapley Additive Explanations, ranks the groups, and turns the top ranked groups into the reason codes sent to the applicant. The United States Patent and Trademark Office granted the patent in July 2024 on an application Discover filed in May 2020. Discover Financial Services merged into Capital One Financial Corporation in May 2025 (the patent assignment was recorded in July 2025), which is why current patent databases list Capital One as the assignee. No source discloses an error rate, approval volume or other outcome for the system.

No outcome disclosed.

Wells Fargo

United States · Banking · 2022

PilotGrade B

Wells Fargo Bank patented a computer based credit evaluation system that pairs a machine learning credit risk model with an adverse action methodology: when the model denies an applicant, the system compares the applicant's characteristic values against anchor values taken from a top scoring population, calculates a replacement score for each characteristic, and ranks the characteristics to identify the principal adverse action factors for the denial. The United States Patent and Trademark Office granted the patent in October 2022 on an application Wells Fargo filed in October 2019. Separately, the trade publication Risk.net reported in August 2021 that a team of Wells Fargo researchers had begun deploying an explainability technique for its deep learning credit models, and a paper by six Wells Fargo model risk researchers proposed a related Shapley decomposition method for explaining adverse credit decisions. No outcome metric or notice volume is disclosed by any source.

No outcome disclosed.

How do you implement it?

A model agnostic playbook: what to prepare, the order to build in, and what goes wrong.

Data you need

  • Ranked reason codes for every adverse decision from the decision engine
  • An approved library of plain language descriptions per reason code, per language
  • Notice templates and regulatory content requirements per product and market
  • Samples of past notices and complaints for testing

Systems to integrate

  • Decision engine or loan origination system
  • Document generation and correspondence system
  • Complaint and case management
  • Customer channels for delivery and follow up questions

Complexity: Medium

Drafting text is easy. The hard parts are reliable reason codes from the model, a reason library that compliance owns, and automated checks that make it impossible to state a reason the model did not produce.

  1. 1

    Fix the reason codes first

    Confirm with model risk that the model produces specific, ranked principal reasons that are accurate for each decision. The assistant cannot repair weak reasons.

  2. 2

    Build the reason library

    For every code, compliance approves a customer description, an internal description and, where appropriate, a note on what the customer could change. Keep owners and review dates.

  3. 3

    Constrain the generation

    Pass only the decision's codes and approved descriptions to the model and forbid any other reason. Use templates for the legally required parts of the notice.

  4. 4

    Verify every draft

    Add an automated check that maps each stated reason back to a code and blocks the draft on any mismatch, omission or prohibited term.

  5. 5

    Review, measure, then automate

    Start with human review of every draft, measure the error rate, and allow automatic sending per product only when the error rate is proven near zero.

Guardrails

  • The draft may only contain reasons present in the decision record
  • Every principal reason in the decision record must appear in the notice
  • No protected characteristic or proxy may appear as a reason
  • Legally required elements come from templates, not from generation
  • Every sent notice is stored with the decision record and the codes it was built from

KPIs to instrument

  • Share of drafts that pass the automated reason check first time
  • Error rate found in human review and in sampling after launch
  • Time to issue a notice after the decision
  • Complaints and reconsideration requests that mention unclear reasons

Human in the loop

Compliance owns the reason library and approves templates. Reviewers approve drafts until the measured error rate allows automatic sending, and a human answers any dispute or reconsideration request.

Common failure modes

Invented or softened reasons
A fluent model adds a plausible reason or blurs the real one. Block any reason that does not map to a code.
Reasons that are accurate but useless
Codes that describe model internals mean nothing to customers. Invest in the reason library, not only the model.
Drift between model and library
A model update adds or renames features and the library falls behind. Tie library review to model change control.

What are the risks and rules?

EU AI Act

Depends on design

The drafting assistant does not assess creditworthiness, so on its own it is not the Annex III point 5(b) credit scoring system. It helps the lender meet the Article 86 right of affected people to a clear and meaningful explanation of decisions based on such a high risk system. If it is built into the scoring system it shares that system's high risk obligations; as a separate drafting tool its tier depends on its design and on how its output is reviewed. The follow up chat assistant must tell customers they are dealing with an AI system (Article 50).

Guidance

Controls to put in place

  • Reason library under compliance ownership with version history
  • Automated reason to code reconciliation on every draft
  • Sampling of sent notices against decision records, reported to compliance
  • Change control that links model releases to reason library review

Frequently asked questions

Can a generative model write adverse action notices?
It can draft them, but only from the reason codes the credit model produced and with an automated check that nothing was added or left out. The legally required parts should come from templates.
Does using AI change the duty to explain credit decisions?
No. In the US, Regulation B requires specific reasons that describe the factors actually considered or scored, whatever the technology. The CFPB withdrew its 2022 circular on complex algorithms in May 2025, but the notice requirements in 12 CFR 1002.9 and their official interpretation are unchanged. In the EU, the Court of Justice has ruled that a person subject to an automated credit assessment must be told the procedure and principles actually applied, in an intelligible way, and the EU AI Act adds a right to an explanation for decisions based on high risk systems such as credit scoring.
Which named lenders have this documented?
Wells Fargo Bank holds a patent, granted in October 2022, for an adverse action methodology that ranks the characteristics of a machine learning credit risk model to identify the principal reasons behind a denial. Trade press reported in August 2021 that a Wells Fargo team had begun deploying an explainability technique for its deep learning credit models. Discover Financial Services holds a related patent, granted in July 2024, that turns Shapley based explanations of a credit model into adverse action reason codes. Both are the lender's own patent filings rather than a disclosed error rate or notice volume, so they show that the methodology is real and built, not that it runs at full production scale.

How to cite this page

Blits.ai AI Use Case Library, "AI drafted explanations for credit declines and adverse actions", last verified 27 September 2026, https://www.blits.ai/ai-use-cases/adverse-action-explanations. Licensed under CC BY 4.0. Method: how we verify use cases.

Changelog
  • 27 September 2026: First published

Related use cases

BankingPayments and cards

AI credit scoring with alternative data for thin file applicants

A machine learning credit model that adds consumer permissioned alternative data, such as bank account cash flow, rent, utility and telco payments or ecosystem data, to credit bureau data, so a lender can assess applicants with thin or no credit files and return a decision with specific reasons.

Deployments
5 public, best grade B
Autonomy
Supervised agent
Banking

AI cash flow underwriting for small business loans

An underwriting engine that assesses a small business's repayment capacity from live bank transactions, point of sale and payment flows, receivables and accounting data instead of audited accounts, and returns a decision recommendation with the evidence and reasons behind it.

Deployments
4 public, best grade B
Autonomy
Supervised agent
Cross industryBanking

AI for drafting customer letters and outbound notices

AI that drafts the letters and notices operations must send at scale, such as arrears notices, decline letters, complaint responses, servicing confirmations and product change notices, from case data and approved templates and clauses, in the customer's language, for a person to approve where the notice is regulated.

Deployments
5 public, best grade B
Reported cycle time reduction
25%
SS&C GIDS and RS, vendor claim
Banking

Conversational AI for loan application intake

A conversational assistant on web, app, messaging or voice that explains loan products, captures the application through dialogue in the customer's language, checks documents and basic eligibility rules, and hands a complete, structured application to origination, without making the credit decision.

Deployments
5 public, best grade C
Autonomy
Supervised agent
Banking

AI recommendations for loan restructuring and hardship arrangements

An assistant that assembles a stressed borrower's position, tests restructuring options such as a term extension, rate relief, payment holiday or due date change against policy and affordability, and recommends the best fit with a written rationale for a person to approve.

Deployments
1 public, best grade B
Autonomy
Copilot