§ About

How stimmo turns an address
into a verdict.

A six-step pipeline, one coefficients file, no machine learning. Same inputs, same output — every time.

Methodology
v0.24.2 · 2026-1
42 OMI
microzones · Milano
Fair-price check for Milan apartment listings — OMI-anchored, no machine learning, every multiplier visible. Built by Alessandro Diaferia. stimmo is open source — view the code on GitHub.
Wordmark · Instrument Serif
stimmo
A transparent, OMI-anchored fair-price check
for Milan apartment listings.
Numerals · JetBrains Mono
€ 6 825 / m²
OMI band 5 800 – 7 200 €/m² · zone B5 · semester 2026-1
fair over under Verdicts

The pipeline

§ Address → verdict · 6 steps
  1. 01

    Geocode

    OSM Nominatim resolves the address to lat / lon. Queries are restricted to Milano comune.

  2. 02

    Locate the OMI zone

    Point-in-polygon against Milano's official OMI microzone shapes.

  3. 03

    Pull the €/m² band

    Compr_min – Compr_max for that zone × property type × condition bucket.

  4. 04

    Count amenities

    OSM Overpass — schools, transit, markets, pharmacies, parks within 500 m.

  5. 05

    Adjust the band

    A single coefficients table multiplies floor, lift, size, condition, energy, outdoor, era, orientation, exposure, room density, second bathroom, parking box, and amenities.

  6. 06

    Classify

    Compare asking price to an ask-shifted band (rogito + 6 %). ±5 % around it is fair.

Want the €/m² band for a specific neighborhood without pasting a listing? Browse every Milano OMI zone →

Data sources

42 microzones · Milano · 2026-1

OMI quotations

Agenzia delle Entrate · Bundled · CKAN

Per-zone €/m² ranges for sales, split by property type and condition (Normale / Scadente / Ottimo). The spine of every estimate.

License
IODL 2.0
File
data/assets/milano_omi_valori.csv
1 comune · no metropolitan belt

OMI zone polygons

Comune di Milano · Bundled · GeoJSON

Microzone shapes used for point-in-polygon zone assignment. Comune di Milano only — addresses outside the comune are rejected.

License
IODL 2.0
File
data/assets/milano_omi_zones.geojson
8 semesters · ~4 years

OMI history

Agenzia delle Entrate · Bundled · CSV

Trailing 8 semesters (~4 years) of bands per zone × type × condition. Drives the trend strip on the report.

License
IODL 2.0
File
data/assets/milano_omi_history.csv
Q quarterly · by surface bucket

NTN — transactions

Agenzia delle Entrate · Bundled · CSV

Numero di Transazioni Normalizzate, quarterly. Shown for market context only — never used as a pricing input.

License
IODL 2.0
File
milano_ntn_total.csv · milano_ntn_by_size.csv
1× request per estimate

Nominatim — geocoding

OpenStreetMap · Live · 1 req/s

Free geocoder, called once per estimate. Queries are scoped to Milano to avoid stray matches.

License
ODbL
File
nominatim.openstreetmap.org
500 m radius · 6 categories

Overpass — amenities

OpenStreetMap · Live · 500 m

Counts of schools, pharmacies, markets, transit stops and parks within 500 m. If unreachable, the estimate still renders with a zero amenity score and a warning.

License
ODbL
File
overpass-api.de
Principle · 01

No machine learning.

stimmo has no trained model. Valuation multipliers live in a single file — valuation/adjustments.py — and transaction-cost rates in another, costs/rates.py. Every valuation multiplier (floor, lift, size, condition, energy, outdoor, era, orientation, exposure, room density, second bathroom, parking box, and amenities) lives in the first, in plain Python.

The verdict is deterministic: same inputs, same output. If you disagree with a coefficient, you can read the line where it lives, change it, and re-run.

valuation/adjustments.py → valuation/engine.py → verdict.classify()
Principle · 02

Ask-shifted, not rogito.

OMI publishes transacted prices — what changed hands at the notary, after negotiation. In Milano, asking prices typically run 5–10 % above the eventual sale price.

OMI rogito
€ 6 090 € 7 560 / m²
+ 6 % ask
€ 6 456 € 8 014 / m²
shift +6 %

We shift the OMI band upward by a fixed +6 % ask-premium before classifying. ±5 % around the shifted band is "fair". The constant lives in verdict.py::ASK_PREMIUM_PCT.

What buying it costs

The price is not the whole bill. Taxes, notary, agency, mortgage and any renovation come on top, so the report also shows an estimate of what the purchase really costs.

It is a separate, deterministic calculation with its own rates file, costs/rates.py, and it never feeds the verdict, which still comes only from the valuation coefficients above. Taxes follow the statutory formulas; fees and renovation are published ranges, and any range we could not confirm as current is labelled indicative. Where an input is missing, such as the rendita catastale that listings rarely state, the figure is shown as a range rather than guessed.

What stimmo doesn't model

Spese condominiali

Routine condominium fees and extraordinary works (lavori straordinari deliberati). Can shift true cost €10–50 k. Invisible to OMI.

Piano nobile

The classic 1° piano premium in storied buildings. Inside the same building, can drive ±5–10 %.

Street noise & view

A unit on a quiet cortile vs. one on Corso Buenos Aires. OMI averages, doesn't see this.

Comparable listings

Italian per-transaction sale data isn't public. We don't fit a model on stale asking prices — by design.

Metropolitan belt

Sesto, Cinisello, Cologno, Rho — outside the Milano comune polygon. Will fail with "outside Milano".

Commercial property

Shops, offices, ateliers — different OMI category, different dynamics. Residential subtypes only.

not a perizia
fairness check · v0.24.2

stimmo is a fairness check, not an official appraisal.

It does not replace a qualified perito and should not be used as the basis for legal, fiscal, or contractual decisions. Use it to sanity-check an asking price, negotiate, or walk away — not to sign anything.

Run an estimate → Install the bookmarklet
Built by Alessandro Diaferia. stimmo is open source — view the code on GitHub. Have a feature request, found a bug, or want to suggest an improvement? Open a GitHub issue →