terry@aequum.ai DISPARITY ESTIMATION & COMPLIANCE INFRASTRUCTURE  ·  PATENT-PENDING  ·  NO-EGRESS DEPLOYMENT
Patent-pending disparity estimation · Daubert-defensible

You Can't Ask Their Race. Regulators Expect You to Know Anyway.

When self-reported race data is unavailable, most compliance tools rely on a widely-used proxy method that systematically understates racial disparities — creating exam and litigation exposure institutions don't see coming until it's tested. CREST replaces that guess with a measurement built to hold up under regulatory exam and in court.

Getting this wrong is expensive — and it's not hypothetical

Someone has to estimate race when it isn't self-reported — for HMDA fair lending analysis, a CRA exam, or a discrimination claim in litigation. If that estimate is wrong in a way that systematically favors the institution, examiners and opposing counsel will eventually find it. “Our vendor's tool produced the number” is not a defense that holds up once it's actually tested — and the tools built to make this simple were never built to survive that test.

CREST-Delta · New

Where PPP forgiveness went — and where it didn't, by neighborhood.

Within five miles of a community bank — and the loan went elsewhere anyway.

During the Paycheck Protection Program, minority-owned businesses disproportionately borrowed through a nationwide platform channel that forgave loans at markedly lower rates than branch-based community banks. Most were not remote — they sat inside the everyday footprint of a community bank that, on its own record, forgave at a far higher rate.

$4.73B
Forgiveness not received nationally
300,436
Businesses affected
76.9%
Forgiveness rate received
94.0%
Community-bank standard
The research behind the map
Sorted Out: Effective Access, Lender Sorting, and Racial Disparities in PPP Loan Forgiveness
Under review · Review of Financial Studies

Chalavadi, Leitch & Pastor. Decomposes the forgiveness gap into within-lender and between-lender components, and traces the between-lender share to sorting into a nationwide platform channel — not to physical distance from a community bank.

Read the Paper

The compliance layer, and the engine beneath it

CREST produces the defensible disparity estimate. STRATA is the validated inference engine that feeds it — available on its own as a hosted API or a private no-egress deployment.

Featured · Compliance & Disparity Estimation Engine
CREST

CREST quantifies how much legacy proxy methods understate discrimination — producing defensible disparity estimates for compliance self-testing, regulatory exam support, and litigation.

Used by
  • Financial institutions for fair lending self-testing and exam defense
  • Insurers meeting NAIC proxy-testing mandates and Colorado's SB 26-189 transparency law (effective Jan. 2027)
  • Applicable across fair lending, employment, insurance, housing, healthcare, and criminal justice
Pricing
  • Enterprise — includes full STRATA imputation$100,000 / yr
  • Standalone — litigation & consulting$15,000 / matter
The engine beneath CREST
STRATA — Race & Ethnicity Imputation API

The validated ML inference engine beneath CREST. LSTM + geographic → XGBoost pipeline, validated independently on a 981,000-record HMDA holdout and a 1.07M-record PPP external validation — two separate validations on two separate populations; neither substitutes for or confirms the other. Available as a hosted API or a private no-egress deployment for regulated institutions.

  • Free tierto 100K rows/mo
  • Starter$1.00 / 1K rows
  • Growth — 1M–10M$0.75 / 1K rows
  • Scale — 10M+$0.50 / 1K rows
  • AWS Marketplace$0.03 / 1K rows
  • STRATA Premium — no-egress$20,000–$45,000 / yr

Why existing tools get this wrong

01

BISG's errors are SES-correlated, not random

Minorities in wealthier areas are misclassified as White; Whites in poorer areas are misclassified as non-White. The result: measured Black–White approval disparities are understated by approximately 43% in small-business lending (Greenwald et al., J. Financial Economics 157 (2024), 103857). CREST corrects for this structure — not just the headline accuracy number.

02

Outperforms the alternatives on the same ground truth

STRATA outperforms BISG, BIFSG, ZRP, and all major open-source alternatives on HMDA and PPP ground truth — but the durable moat is the compliance layer, not the benchmark.

43%
BISG downward bias · Greenwald et al. 2024
89.2%
General STRATA model accuracy · arXiv:2505.16946

CREST's bias simulation and disparity estimation methodology is patent-pending (application 64/067,906).

Built from federal-grade methodology

The STRATA pipeline grew out of SSA race/ethnicity modeling work. The same rigor that supports federal agency analysis — reproducible, versioned, auditable — is now available as a commercial API and compliance platform.

Two deployment modes for every buyer

Hosted API for researchers, fintechs, and advocacy organizations. Private AWS container for banks, insurers, and mortgage lenders where PII cannot leave the institution's environment. Data never leaves your infrastructure in the Premium tier.

Published and peer-reviewable

arXiv:2504.21259
LSTM + Geographic → XGBoost race imputation pipeline
Chalavadi, Pastor & Leitch (2025)
Read abstract
arXiv:2505.16946
STRATA: A Name-and-Geography Race Inference Model for Residential Deed Records
Chalavadi, Leitch & Pastor (2025)
Read abstract
SSRN · rev. Aug 2026
Investor Entry and the Changing Ownership of Urban Housing: Evidence from New York City
Chalavadi, Pastor & Leitch — working paper, aequumAI LLC
Read paper
SSRN · Aug 2026
Sorted Out: Effective Access, Lender Sorting, and Racial Disparities in PPP Loan Forgiveness
Chalavadi, Leitch & Pastor — under review, Review of Financial Studies
Read paper
Live demo
Enhanced HMDA Report — STRATA + CREST in action
Four synthetic institutions scored under one shared CREST seed
hmda.aequum.ai

Ready to talk?

Whether you're a compliance team preparing for exam, counsel quantifying discrimination harm, an insurer facing proxy-testing mandates, or a researcher — we'd like to hear from you.

AWS Marketplace

View the STRATA listing

Location

aequumAI LLC
New York