AI Mortgage Pricing Disparate Impact Analysis Playbook

A $6B community bank's fair lending team is preparing for an OCC examination. The mortgage portfolio has 4,200 originations in the prior 12 months. Preliminary analysis suggests Black borrowers are paying 18 basis points more in APR than similarly qualified white borrowers after controlling for FICO and LTV.

When to use this playbook

• Use this playbook when the decision looks like the situation above: A $6B community bank's fair lending team is preparing for an OCC examination.
• It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "Mortgage Pricing Disparate Impact Analysis".
• Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.

What you'll need

• HMDA LAR for the past 12 months (4,200 originations)
• Loan-level pricing data (APR, rate, points, fees)
• Borrower credit attributes (FICO, LTV, DTI, loan purpose, property type)
• Loan officer identifier by loan
• Bank's pricing policy and exception procedures

Attachments: Multiple attachments (Spreadsheets, Documents)

You are a fair lending analyst conducting a disparate impact analysis on a community bank's mortgage portfolio ahead of an OCC examination. I am attaching:

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

Produce:
1. Run a regression analysis controlling for all legitimate pricing factors (FICO, LTV, DTI, loan type, loan officer) and quantify the residual APR disparity by race and national origin.
2. Identify whether the disparity is concentrated in specific loan officers, branches, or loan products—the OCC will want to know the source.
3. Assess whether loan officer pricing discretion (exception policy) is contributing to the disparity: are exceptions granted at higher rates to white borrowers?
4. Calculate the remediation amount: what would affected borrowers have paid under race-neutral pricing?
5. Tell me whether this rises to a pattern-or-practice finding and what voluntary remediation steps reduce OCC examination risk.

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

What to expect

• Regression analysis results with residual disparity quantification
• Concentration analysis by loan officer and branch
• Pricing exception disparity assessment
• Remediation amount calculation
• OCC examination risk assessment and voluntary remediation options

Review before you act

• Validate this output against source files before relying on it: Run a regression analysis controlling for all legitimate pricing factors (FICO, LTV, DTI, loan type, loan officer) and quantify the residual APR disparity by race and national origin.
• Validate this output against source files before relying on it: Identify whether the disparity is concentrated in specific loan officers, branches, or loan products—the OCC will want to know the source.
• Validate this output against source files before relying on it: Assess whether loan officer pricing discretion (exception policy) is contributing to the disparity: are exceptions granted at higher rates to white borrowers?.
• Validate this output against source files before relying on it: Calculate the remediation amount: what would affected borrowers have paid under race-neutral pricing?.
• 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.