# 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.

- Topic: Data & Analysis
- Framework: Few-Shot
- Level: Standard
- Tags: Finance, Data & Analytics, Analyze, Plan, Fill-in Template
- Source: https://www.thinkwithprompt.com/prompts/run-a-fair-lending-review-of-loan-pricing-and-approval-data

## Prompt

```text
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.
```

## What to fill in

- DATES
- PASTE

Free to copy and use. From ThinkWithPrompt (https://www.thinkwithprompt.com/), a library of 2,663 curated AI prompts.