D
SellSignal
How It Works

How Sell Signal Works

Sell Signal scores approximately 1.1 million NYC residential properties on their likelihood of selling within the next 12 months. Six independent scoring layers surface the properties most likely to transact — so you know who to call and when.

The Base Rate Problem

In a typical year, only 30,000–50,000 of NYC's 1.1 million residential properties change hands — a base rate of just 3–4.5%. A model that predicts "no sale" for every property would be 96% accurate. Sell Signal has to dramatically beat this by concentrating high scores on the 3–4% that actually transact.

2020
2.3%
COVID floor
2021
5.0%
Rebound
2022
3.8%
Rate shock
2023
2.9%
Trough
2024
3.2%
Recovery

6-Layer Scoring Architecture

Each layer captures a different category of sell signals, scored independently, then combined into a composite probability score. This modular design means layers can be refined or added without redesigning the core engine.

25%
15%
20%
15%
15%
10%
L1: Ownership & Equity
L2: Property & Building Events
L3: Market Context
L4: Listing & Transaction History
L5: Life Events & Demographics
L6: Behavioral & Digital

L1: Ownership & Equity

25%

How long the owner has held the property and how much unrealized equity they've accumulated. The median hold before sale in NYC is ~9 years.

Ownership durationUnrealized equity gainAbsentee / out-of-state ownerLLC / corporate ownershipEstate or trust transferMortgage maturity

L2: Property & Building Events

15%

External pressure events that create sell motivation — expiring tax abatements, assessment spikes, distress indicators.

421a / J-51 expirationAssessment spikePre-foreclosure / tax lienNearby constructionRent stabilization (negative)Building conversion

L3: Market Context

20%

Is this a good time to sell in this specific location? These signals don't predict who will sell, but when selling is attractive.

Building sales velocityNeighborhood price momentumInventory tightnessComp pricing gapDays on market trendInterest rate environment

L4: Listing & Transaction History

15%

The most directly predictive signals — this owner has already demonstrated intent to sell.

Expired listingWithdrawn listingMultiple price reductionsFailed contractTransaction frequencyBuyer demand (saves)

L5: Life Events & Demographics

15%

Life changes that commonly precede residential transactions — court filings, age, relocation, family changes.

Divorce filingProbate / estate proceedingOwner ageJob relocationGrowing familyFinancial distressRetirement

L6: Behavioral & Digital

10%

Digital behavior suggesting an owner is thinking about selling. Being built incrementally.

Owner searches own addressValuation tool usageMonitors building listingsAgent inquiry

Score Tiers

TierScoreP(Sale)
Very High80–100>40%
High60–7915–40%
Moderate40–595–15%
Low20–392–5%
Very Low0–19<2%

Why NYC-Specific Matters

National propensity models miss the signals that matter most in New York. Sell Signal is built on NYC-specific data that no national model can access:

ACRIS
Every deed, mortgage, and UCC filing — the richest public property transaction database in the country
DOF Records
Assessed values, tax class, 421a/J-51 abatement schedules, ownership history
REBNY RLS
Full listing history — expired, withdrawn, price-reduced, and active
Court Filings
Divorce, probate, and lis pendens — direct life event signals from public record
Rent Stabilization
DHCR status — these units almost never trade, and the model knows it
Marketproof Data
Building-level sales velocity, comp gaps, and buyer demand signals from our platform

Data Sources

DataStatus
Ownership history & transfersLive
Sale prices & datesLive
Mortgage recordingsLive
Owner name & LLC detectionLive
Assessed value & tax classLive
Listing history (expired, withdrawn)Live
Building sales velocityLive
421a / J-51 abatement schedulesLive
Price reductionsLive
Failed contractsLive
Rent stabilization statusLive
Comp pricing gapComing
Neighborhood price momentumComing
Days on market trendsComing
Lis pendens / pre-foreclosureComing
Tax liensComing
DOB permits (nearby construction)Coming
Buyer demand (saves / favorites)Future
Divorce filingsFuture
Probate / estate proceedingsFuture
Owner estimated ageFuture
Relocation signalsFuture
Owner searches own addressFuture
Valuation tool usageFuture
Agent inquiry signalsFuture

Early Validation

Tested on 26 real NYC properties across three cohorts — the algorithm correctly orders sold properties above expired listings above stable long-term holds:

Sold
59.5
mean score (n=10)
Expired
52.8
mean score (n=8)
Stable
48.0
mean score (n=8)

Cohen's d: 0.73 (good effect size) · Label-Score Alignment: 95.9% · Ordering: SOLD > EXPIRED > STABLE ✓