AI Adverse Action Notice Compliance Review Playbook

A consumer lender processes 12,000 applications monthly and sends adverse action notices via automated system. A compliance audit found that 8% of notices use generic reason codes that may not accurately reflect the actual denial reason. The CFPB's examination manual flags non-specific notices as a top violation.

When to use this playbook

• Use this playbook when the decision looks like the situation above: A consumer lender processes 12,000 applications monthly and sends adverse action notices via automated system.
• It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "Adverse Action Notice Compliance Review".
• Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.

What you'll need

• Sample of 500 adverse action notices with reason codes
• Corresponding loan application data and credit decision records
• Credit bureau reason codes and the lender's internal reason code mapping
• CFPB examination manual section on adverse action
• ECOA Regulation B requirements for adverse action notices

Attachments: Documents (Documents)

You are a compliance officer reviewing adverse action notice accuracy for a consumer lender. I am attaching:

Work only from the attached source files. If a conclusion is not supported, say so.

Produce:
1. For each of the 500 sampled notices, assess whether the stated reason codes accurately reflect the actual denial reason in the credit decision record.
2. Identify the specific notices where the reason code is generic (e.g., 'credit score' when the actual reason is 'insufficient income') and calculate the error rate by loan type.
3. Assess whether any of the inaccurate notices could constitute a UDAP (unfair, deceptive, or abusive act or practice) violation—notices that mislead consumers about why they were denied.
4. Recommend the specific reason code mapping changes needed and estimate the number of affected consumers who may have been misled.
5. Tell me whether retrospective notice correction is required and what the CFPB civil money penalty exposure is at current error rates.

Call out where independent models are likely to disagree, and list follow-up documents a reviewer should request.

What to expect

• Adverse action notice accuracy rate by loan type
• Inaccurate notice inventory with specific errors
• UDAP risk assessment
• Reason code mapping correction recommendations
• Retrospective correction obligation and CFPB penalty exposure

Review before you act

• Validate this output against source files before relying on it: For each of the 500 sampled notices, assess whether the stated reason codes accurately reflect the actual denial reason in the credit decision record.
• Validate this output against source files before relying on it: Identify the specific notices where the reason code is generic (e.g., 'credit score' when the actual reason is 'insufficient income') and calculate the error rate by loan type.
• Validate this output against source files before relying on it: Assess whether any of the inaccurate notices could constitute a UDAP (unfair, deceptive, or abusive act or practice) violation—notices that mislead consumers about why they were denied.
• Validate this output against source files before relying on it: Recommend the specific reason code mapping changes needed and estimate the number of affected consumers who may have been misled.
• Confirm every cited figure, date, counterparty, or requirement against the attached originals — models compress and can drop a qualifier.
• Treat disagreement between models as a review item, especially on classification, materiality, and recommended next action.
• Do not authorize an operational, clinical, legal, credit, or enforcement action solely because the models agree.