By subscribing you agree to our Privacy Policy and provide consent to receive updates from our company. You can unsubscribe at any time.
© 2026 Polygon Research. All right reserved.
Scan 02 · Marketing
A marketing scan compares who applied to you with who lives in the market you serve, by race and ethnicity together. HMDAVision builds it from loan-level HMDA against Census population, tracks the gap across four years, and converts it into the number of applications that would close it.
Free tier is three answers a day, fifteen a month, no card.
Start here
Regulation B prohibits any statement or practice, in advertising or otherwise, that would discourage a reasonable person from applying on a prohibited basis.
Regulation B, 12 CFR 1002.4(b)
Marketing risk is the quiet version of a fair lending problem. No one is denied. The applications simply never arrive from part of the market, and the application register shows it before any complaint does. The scan measures that absence.
01
A gap that holds for years
The same group under-represented in applications across every HMDA release, with no trend toward closing.
02
A gap peers do not show
Lenders of similar size in the same market receiving applications from a group at a rate you are not.
03
Thin applications where population is dense
Tracts with a large share of a group and few applications from it, which the redlining map shows directly.
04
A blended average hiding a split
Hispanic White and Hispanic of two or more races moving in opposite directions inside one Hispanic total.
05
Growth that widens the gap
Total applications rising while the under-represented group's share stays flat or falls.
06
Channel doing the sorting
One group arriving mostly through brokers or correspondents while another arrives through retail.
The scan itself
Minority Detail crosses race with ethnicity, so each row is a specific group rather than a blended average. The 2022 to 2025 gap columns show whether the distance is closing. The last column converts the current gap into applications.
One metro, all lenders, 2025 applications from HMDA against Census population, applications with race or ethnicity not available excluded. Select your institution and the same table shows your own mix against the same people.
What the scan says
Non-Hispanic Black residents are 8 percent of this market and 5 percent of its applications. The gap has held between 2.2 and 2.7 points since 2022. Closing it at the market level takes 598 applications; your share of that is your target.
Applications where race or ethnicity was not reported are excluded. A lender with a high not-available share has a data question before a marketing one.
Whether the gap is the whole market's or yours alone. A gap every lender shares is a demand question. A gap only you show is a reach question.
The workflow
Each step is a set of filters in HMDAVision. Keep them and the scan reruns on the next HMDA release in minutes.
1
Define the market you serve
Assessment area, field of membership, or the geography your lending and advertising reach. The population baseline is built from it.
Output: a defined market with a documented rationale.
2
Read the market-level table first
All lenders, all groups, four years of gaps. This is the demand picture your own numbers will be read against.
Output: which gaps belong to the market, and which do not.
3
Select your institution
The same table, your applications only. Compare each row's gap to the market row and to peers of similar volume.
Output: the groups where your reach trails the market.
4
Convert the gap to applications
The last column does the arithmetic. It is the number a marketing plan and a compliance memo can both use.
Output: an application target by group.
5
Locate it on the map
Open the redlining view with the same filters. The tracts where population is dense and your applications are thin are where the target lives.
Output: a target with a geography attached.
6
Record the filters and repeat
Year, geography, action type, group definition. The next release shows whether the gap moved.
Output: a trend line, and an audit trail.
From finding to action plan
A compliance officer reads 598 applications as exposure. A marketing lead reads it as demand no campaign is reaching. Same table, same afternoon. What changes is who is looking and what they do next.
Advertising that reaches the whole market is both a Regulation B expectation and the cheapest source of applications you are not receiving. The tract list from step five is the media plan.
The lenders already receiving those applications show which agents, builders and community organizations are in the flow. The referral partner view names them by tract.
Rerun the same filters. A gap that narrows is evidence of a working program, produced by you rather than purchased.
Start scanning
Ask one question at mortgagedata.ai, or open the full table on your own institution with a guided seven-day trial of HMDAVision.
Polygon Research is a research and analytics firm, not a law firm. Nothing here is legal advice, and a fair lending program should be built with counsel.
Keep going
Scan 01
Redlining
Your footprint against tract demographics, and who lends in the tracts you skip.
Scan 03
Underwriting
Denial disparity, denial reasons and the Minority Delta by loan purpose.
Scan 04
Pricing
Higher-priced lending, rate spread and fees against the market.
Scan 05
Steering
Product, term and channel distribution across borrower groups.