themortgagellm^™

What it does

Gradient-boosting classifier rating the probability that a conventional conforming loan will be granted an appraisal waiver — either Fannie Mae's Value Acceptance (formerly Property Inspection Waiver / PIW) or Freddie Mac's Automated Collateral Evaluation (ACE) — instead of requiring a traditional full appraisal. Trained on Fannie Mae Single-Family Performance Data and Freddie Mac STACR acquisitions, 2018-2023 originations (22.4M loans after filtering out Freddie's pre-2021 unpopulated rows), tested on 2024-2025 (2.6M loans): AUC 0.85 (cross-cycle holdout; random-split within 2018-2023 gives AUC 0.93). Isotonic-calibrated; calibration is near-perfect (ECE = 0.0008 on test). The positive class bundles pure waiver ("Waiver Only") with Fannie's 2024 Value-Acceptance-Plus-PDC expansion ("Waiver + Property Data") — both are appraisal-free from the borrower experience. Empirical waiver rate ~30% in train, ~18% in OOT (the GSE programs tightened after the 2020-2021 expansion).

Why it matters. When a loan qualifies for an appraisal waiver, the borrower saves ~$500-700 on the appraisal fee, and the file closes 7-10 days faster (no appraiser scheduling, no comparable-sales review cycle). On the lender side, waiver-eligible files require less collateral-specific QC and free up appraisal-management capacity for the loans that actually need it. So knowing the waiver probability before running the file through DU/LPA is operationally useful for LO intake messaging, pricing strategy (tighter rate/cost quotes when waiver is likely), and pipeline planning.

What it is NOT. The GSE's authoritative waiver decision uses property-specific data that lives only inside Fannie/Freddie — the depth of their Collateral Underwriter database on the subject address, comparable-sales density in the neighborhood, prior valuation history on the property. This model captures the structural-eligibility signal from the features we DO have (loan purpose, LTV, FICO, occupancy, property type, vintage, originator) but cannot match the GSE's precision on property-level questions. Position it as a pre-DU/LPA heuristic, not as a substitute for AUS.

Universe note. Only scores conventional conforming loans (Fannie/Freddie acquired). FHA / VA / USDA / jumbo / portfolio-held loans follow entirely different appraisal regimes and are out of scope. For those, you'd consult HUD's eAppraiser, VA's appraiser panel, or the lender's own portfolio collateral policy — not a GSE waiver model.

› Try it on the home page (Loan-level model scoring → Appraisal Waiver Probability)

API connector

Programmatic access. Calibrated probability + risk band + operating recommendation in the response.

POST /api/score_piw
Content-Type: application/json

{
  "source": "FNM_SFP",              // 'FNM_SFP' or 'FRE'
  "loan_purpose": "Refinance",      // strongest single driver
  "occupancy": "Owner-Occupied",
  "property_type": "Single Family",
  "borrower_fico": 740,
  "original_ltv": 70,
  "original_cltv": 70,
  "dti": 36,
  "original_upb": 350000,
  "original_interest_rate": 6.25,
  "first_time_homebuyer": "N",
  "number_of_units": 1,
  "product_type": "FRM"

  // Optional: "seller_name" (your originating lender) and
  //           "property_state" add finer-grained signal. Omit them and
  //           the model uses the population-baseline pattern.
}

Note: The probability is a structural-eligibility signal, not a guaranteed outcome. For the authoritative waiver decision, run the file through Desktop Underwriter or Loan Product Advisor — the GSE's models see property-level data this model cannot.

Schema reference (request / response shape): GET /api/score_piw/schema

Model metadata (training cohort, AUC, calibration): GET /api/score_piw/info