Skip to main content
Quant

Quant for CRE.
Math you can defend in IC.

Once your data is clean, we layer the models institutional quant funds run on capital markets, adapted for CRE. Regression. Forecasting. Monte Carlo. Predictive scoring. Every output cites lineage. The AI never invents a number.

All Services

Pipeline Score · Active Deals

Live · Refreshed 6:00 AM

Pursue

3

Watch

1

Pass

1

94

score

Magnolia Lofts

Austin TX · 215 units

PURSUE

87

score

Cypress Creek

Houston TX · 350 units

PURSUE

81

score

Riverside Tower

Tampa FL · 320 units

PURSUE

64

score

Park Place

Phoenix AZ · 180 units

WATCH

42

score

Brookhaven

Atlanta GA · 192 units

PASS

Inputs: deal fit · seller propensity · submarket supply · time-to-close

Regression-scored

Quant spans every phase. Quant-ready during Build. Models ship through Scale. Defensible answers to every deal, market, and hold.

Pipeline Intelligence

Score every deal. Rank the pipeline.

Deal scoring against your investment view. Seller-propensity models surface owners likely to sell. Time-to-close forecasts prioritize what will actually transact.

  • Deal fit score: vintage, micro-location, supply, capital stack
  • Seller-propensity scoring on historical ownership turnover
  • Broker performance: hit rates, mark-to-market accuracy
  • Time-to-close forecasts so the team focuses on what closes

Submarket Score · Sunbelt MF

Zip-Level

Strong

3

Good

3

Austin

78704

92

Houston

77024

85

Tampa

33602

78

Dallas

75201

74

Orlando

32801

68

Charlotte

28202

64

Phoenix

85016

56

Nashville

37203

51

Atlanta

30309

44

75+ Strong
60-74 Good
<60 Watch

Refreshed daily

Market Intelligence

Zip-level signal. Submarket scoring.

Supply pipeline, demographics, rent growth, and rates fused into a single submarket score. Automated daily across every market you target.

  • Zip-level supply pipeline plus demographic and migration data
  • Submarket scoring surfaces emerging micro-markets early
  • NIMBY and entitlement indicators (where supply will actually get built)
  • Rent-comp regression: how much of variance is signal vs. noise

Variance Attribution · Fund III

YTD NOI vs UW

Net Variance

+$0.42M

vs underwriting

By driver

Rent growth above UW

+$1,240K

Occupancy gain

+$580K

Other income lift

+$210K

Turnover overrun

$420K

Insurance reset

$880K

Tax reassessment

$310K

Lineage: Yardi GL · RealPage rent rolls · CoStar comps. Every number cited.

Portfolio Intelligence

Hold periods. Dispositions. Variance.

Hold-period optimization tells you when to sell. Monte Carlo stresses every hypothesis. Variance attribution explains why actuals diverged from underwriting, traced to source.

  • Hold-period optimization: supply, rent forecasts, cap-rate paths, refi optionality
  • Disposition timing tied to LP waterfall mechanics and fund cycle
  • Variance attribution: actuals vs UW by driver, cited to source
  • Monte Carlo with P10 / P50 / P90 bands on every deal

Hold-Period Optimizer · Cypress Creek

Optimized

Optimal exit

Year 5

22.4%

levered IRR

Levered IRR by exit year

14.2%

Y3

18.6%

Y4

22.4%

Y5

Optimal

21.1%

Y6

18.8%

Y7

UW Exit

Year 7

UW IRR

19.0%

Upside

+340 bps

Operator built

Underwriters who learned to code.

Every signal maps back to a line item your IC already reviews. Pro formas, waterfalls, lease economics. No black boxes. No model in search of a deal.

You set the thesis. The models apply it.

Built by underwriters who learned to code. The math ties. The audit trail is yours.