Housing / Mortgage Vertical -- Sample Snapshot

What your $499 Snapshot report looks like

Full sample: 8-layer determination + 3 fix-first items + 3 distributional-shape charts + counterparty-question rehearsal + independent-verifier declaration. Same structure your lender's actual Snapshot delivers within 3 business days.

Buy your lender's Snapshot — $499 Learn more
Category C -- Insufficient For Fair Housing + CFPB Attestation

This is what a failed mortgage-AI-reproducibility audit looks like — $499 to know if yours is next

10 high-severity distributional-drift events. Cohort H3 decline-lane rate rose 14% -> 62% silently. Your lender's Snapshot uses the same structure -- your data, your AI, your jurisdictional footprint. $499. 3 business days.

Buy $499 in 2 clicks See sample below

Sample scenario

Mid-market mortgage lender (~$2B-$10B annual originations / mid-market bank OR non-bank IMB) running an AI mortgage-underwriting classifier scoring each mortgage application and routing to lane:

  • Auto-Approve Conforming (score 0-33): strong file, GSE-conforming auto-approve
  • Manual Review + Upcharge (score 34-66): tier-adjusted rate + manual verification
  • Decline / Refer non-QM (score 67-100): decline OR refer to non-QM lender w/ higher rate

Silent drift: post-Day 45, Cohort H3 (30-50, near-prime credit, majority-minority zip) systematically over-routed to decline / non-QM lane at 61% vs baseline 14% -- a 47 percentage-point cohort-differential that never triggered an alarm on the lender's origination-dashboard, aggregate-approval-rate report, or loan-loss ratio watch.

Overall Determination

CATEGORY C — INSUFFICIENT FOR ATTESTATION. 10 high-severity distributional-drift events detected. Lender should not represent the mortgage-underwriting AI as Fair Housing Act-defensible, HMDA-reportable-accurate, or CFPB-exam-ready until named remediation completes.

The 3 sample charts (your Snapshot delivers similar for your data)

Rolling mean underwriting-risk score by cohort
Rolling mean mortgage underwriting-risk score by applicant cohort — silent Cohort H3 divergence starts Day 45
Baseline vs recent distribution for Cohort H3
Cohort H3 baseline vs recent underwriting-risk-score distribution — mass shifted into decline / non-QM lane
Lane rate per cohort baseline vs recent
Underwriting lane rate per cohort baseline vs recent — cohort H3 decline / non-QM rate rose materially while others stable

The one sentence your lender's own compliance counsel would care about

The AI mortgage-underwriting engine's decline / non-QM lane rate for Cohort H3 (30-50, near-prime credit, majority-minority zip) rose from 14% to 61% over the audit period — a 47 percentage-point cohort-differential that occurred silently while the lender's origination-dashboard, aggregate approval rate, and loan-loss ratio all showed all-green throughout.

Under the Fair Housing Act (42 USC Sec 3601 et seq.) and ECOA (15 USC 1691 + Regulation B), any AI-driven mortgage-underwriting decision from the affected period sits inside disparate-impact analysis reach. Under CFPB Circular 2022-03, adverse-action reason-code accuracy must be defensible per-decision. Under HMDA, the LAR-reportable outcome must trace to reproducible model state. Under SR 11-7 / OCC Bulletin 2011-12, model-risk-management documentation for the audit period is now materially harder to defend at the next OCC / FRB / FDIC exam.

Regulatory framework applied

AuthorityCitation
Fair Housing Act42 USC Sec 3601 et seq. + HUD Rule 24 CFR 100.500 disparate-impact (2023 reinstatement)
Home Mortgage Disclosure Act12 USC Sec 2801 et seq. -- AI-decision reporting 2026
Equal Credit Opportunity Act15 USC 1691 + Regulation B 12 CFR 1002
Fair Credit Reporting Act15 USC 1681 -- adverse-action notice
CFPB adverse-action AICircular 2022-03 (reason-code accuracy) + Circular 2023-03 (AI-marketing UDAAP)
FHFA Enterprise AI/MLAdvisory Bulletin AB 2021-01
Bank Model Risk MgmtOCC Bulletin 2011-12 + Federal Reserve SR 11-7
Dodd-Frank ATR/QM RuleSec 1400-1500
State AI-decisioningCA, NY, MA, CO, IL licensed-lender AI rules (active 2025-2026)
FTC non-bank lendersSection 5 unfair/deceptive practices

What your lender's actual Snapshot includes

SectionWhat you get
Scope + regulatory frameworkNamed state/charter footprint + FHA + ECOA + HMDA + CFPB + FHFA + SR 11-7 + Dodd-Frank citations scoped to your entity
Sensor summaryIndependent-observer specifics, distinct model family, retention pipeline distinct from your production LOS/POS stack
Findings summaryCount of drift events + high/medium severity + disparate-impact-differential flag + first-drift-day
Overall determinationCategory A / B / C w/ specific meaning + remediation-path recommendation
3 fix-first itemsScoped to YOUR AI surface, YOUR state/charter footprint, YOUR next OCC / FRB / FDIC / CFPB exam cycle
Detailed drift eventsEvery drift event day + type + affected cohort + severity + plain-language detail
Counterparty-question rehearsal5 sample decisions from the target-day w/ cryptographic decision-hash reproducibility verification -- suitable for CFPB supervisory-exam response, DOJ fair-lending referral, HUD complaint reply, or class-cert opposition
Upgrade pathsBaseline ($2,500 / 5 days) OR Enterprise Attestation ($35-55K / 3-6 weeks board-ready) + $499 Snapshot credit applies
Independent-verifier declarationSigned by Kevin Luddy personally
Charts + artifacts3 distributional-shape charts + machine-readable JSON + decision-hash lookup table

Read the full sample report

Full Snapshot Report (markdown) Executive One-Pager (markdown)

Big-4 vs contrarianAI

Deloitte / PwC / EY / KPMG fair-lending-audit engagements + model-risk-management review typically price $200K-$1M+ for equivalent Enterprise scope. contrarianAI delivers the same determination shape + regulator-facing attestation at 5-10% of that price via independent-verifier positioning + tooling-driven delivery. The Snapshot ($499) is the sub-procurement-threshold entry that tests the discipline before any organizational commitment.

$499. Three business days. Your lender's actual Snapshot.

Same structure as this sample. Your lender's data, your lender's AI system, your lender's state/charter footprint, your lender's regulatory-framework citations.

Buy your Snapshot — $499
Snapshot credit ($499) applies to Baseline ($2,500) or Enterprise Attestation ($35-55K) upgrade within 30 days. Direct-buy Stripe. Below-procurement-threshold. Report PDF via email within 3 business days.