Run a fair lending review of loan pricing and approval data
A structured fair lending analysis plan and readout that tests for disparities in approvals, pricing, and exceptions.
The prompt
Help me plan and interpret a fair lending review of our lending decisions.
Products in scope: [e.g. "mortgage", "auto (direct or indirect)", "small business", "credit card"]
Data available: [application-level fields - decision, rate, fees, credit score, DTI, LTV, loan amount, channel, loan officer, exceptions, and demographic data or proxy method]
Period: [DATES]
Concern prompting the review: [routine monitoring, complaint, exam finding, new pricing policy]
Results so far, if any: [PASTE]
Give me:
1. The questions to test: underwriting (approval/denial disparities), pricing (rate, fees, discretionary markups), steering (product or channel placement), redlining (lending patterns by geography), and exceptions (who gets policy overrides).
2. For each, the method: comparison groups, control variables that reflect legitimate credit factors, and the statistical tests to use (e.g. regression with controls, matched-pair file review).
3. How to handle missing demographic data (e.g. proxy methods) and their limits.
4. A readout template: findings table with disparity size, statistical significance, sample size, and whether legitimate factors explain it.
5. Follow-up steps for any unexplained disparity: file reviews, policy changes, remediation analysis.
If I paste results, interpret them cautiously: separate statistical significance from practical significance, and do not conclude discrimination did or did not occur. Do not invent results. Findings should be reviewed by fair lending counsel, ideally under privilege.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Data & Analysis prompts
What to fill in
- DATES
- PASTE
How this prompt is built
This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.
Related prompts
- Explain my Excel model to a non-technical executiveTurns a complex spreadsheet or model into a plain-English walkthrough an executive can follow, trust, and question.
- Analyze my clinic's claim denials and revenue cycle KPIsTurns denial and A/R data into root causes, benchmark gaps, and a prioritized fix list for the front end, coding, and billing teams.
- Turn a vague data request into a clear analysis planConverts a fuzzy stakeholder ask into a scoped plan with the real question, data needed, deliverable, and clarifying questions.
- Clean a messy datasetA step-by-step cleaning plan for duplicates, missing values, formats, and outliers.