Pattern: automated property valuation

Real estate / proptech — automated valuation pattern. Per-segment accuracy, fair-housing parity, image-condition assessment.

A proptech company or lender uses AI to generate property valuations from comparable sales, property features, listing photos, and market data. Banking partners require fair-housing-compliant valuation accuracy; replicating historical appraisal bias is a non-starter.

This pattern shows how to evaluate AVM accuracy and fair-housing parity together.

What's at stake

Risk dimension	Magnitude	Framework
Fair-housing exposure on neighborhood-level valuation disparity	Per-violation civil penalties; consent-decree cost	Fair Housing Act / HUD enforcement
Banking-partner rejection of an AVM with documented bias	Loss of integration agreements, revenue impact	OCC / FRB safety-and-soundness reviews
Bad-loan losses from inaccurate valuations	$50K–$500K per loan in the worst-tail outcome	Industry mortgage-loss benchmarks
Brookings-documented appraisal-undervaluation pattern	$48K average undervaluation in Black neighborhoods	Brookings 2018 / HUD studies

The evaluation pattern

A fairness-aware evaluation runs the AVM against a labeled dataset spanning diverse neighborhoods, price ranges, and property types.

1. Numeric scorer (valuation accuracy) — AVM estimate within ±5% of appraiser ground truth.
2. Custom code grader (geographic disparity) — per-Census-tract or per-MSA disparity in median accuracy. Disparity above the configured tolerance (commonly 1.25× ratio) flags as a regression.
3. Demographic-correlation scorer — accuracy disparity must not correlate with protected-class proxies (race demographics, income tier).
4. Image-condition assessment scorer — for AVMs that incorporate listing photos, condition-extraction accuracy from images is scored separately.
5. Comparable-selection rationale judge (GEPA-tuned against ≥50 appraiser-labeled examples — scored output) — the AI's choice of comparables is defensible against an appraiser's choice.

Don't have labels yet? See Bootstrap a judge before GEPA for the week-1 setup.

Continuous trace evaluation: sampled at 1% of production valuations, daily. Disparity trends visible to compliance and risk committees.

Configuration in code

# Python (SDK)
from layerlens import Stratix
client = Stratix()

geo_disparity = client.scorers.create_code(
 name="geographic-disparity",
 code="""
by_tract = group_by_census_tract(traces, scores)
ratio = max_median(by_tract) / min_median(by_tract)
result = {'passed': ratio <= 1.25, 'disparity_ratio': ratio}
""",
)

valuation_accuracy = client.scorers.create_code(
 name="valuation-accuracy",
 code="result = {'passed': abs(output['estimate'] - expected['appraiser_value']) / expected['appraiser_value'] <= 0.05}",
)

comparable_judge = client.judges.create(
 name="comparable-selection",
 evaluation_goal="Score 1-5: is the AI's choice of comparable sales defensible against an appraiser's selection?",
)

trace_eval = client.trace_evaluations.create(
 trace_set={"tags": {"feature": "avm"}, "sample_rate": 0.01},
 scorers=[geo_disparity.id, valuation_accuracy.id],
 judges=[comparable_judge.id],
 schedule="daily",
)

// TypeScript (REST)
const r = await fetch("https://stratix.layerlens.ai/api/v1/trace-evaluations", {
 method: "POST",
 headers: {
 "X-API-Key": process.env.LAYERLENS_STRATIX_API_KEY!,
 "Content-Type": "application/json",
 },
 body: JSON.stringify({
 trace_set: { tags: { feature: "avm" }, sample_rate: 0.01 },
 scorers: [geoDisparityId, valuationAccuracyId],
 judges: [comparableJudgeId],
 schedule: "daily",
 }),
});

What you get

• Fair-housing disparity becomes a measurement on the dashboard, not a discovery during a regulatory review.
• Banking-partner integration approvals come faster — the evaluation evidence packet shrinks the diligence timeline.
• Per-comp rationale auditability for borrower-facing valuation explanations.
• Pre- and post-deployment block on any model variant that worsens disparity.

Stratix capabilities used

• Custom code graders — geographic-disparity and demographic-correlation
• Judges with GEPA optimization — comparable-selection rationale
• Compare models — variant selection with fair-housing criteria
• Trace evaluations — continuous sampled

Replicate this

Get started: Workflow: Govern describes the cross-team gate this pattern sits under.

• Industry → Real estate
• Use case: AI quality gates in CI/CD
• Concept: Continuous evaluation