How Estiq calculates property values across Estonia
Estiq's automated valuation model uses 180,000+ notarised Maa- ja ruumiamet, tehingute andmebaas transactions, Uber H3 geocell weighting, and monthly data updates to deliver Estonia's most transparent property valuations. Read the full methodology.
1. What the AVM is — and what it is not
Estiq's Automated Valuation Model (AVM) is a statistical tool that produces an instant property price estimate for any Estonian address. It processes verified notarised transaction data from the Maa- ja ruumiamet, tehingute andmebaas (tehingute andmebaas), applies spatial weighting, condition and energy class adjustments, and outputs a price range with a confidence interval.
This is not an EVS 875 certified appraisal
Estiq's AVM is a statistical estimate. It does not include a physical inspection of the property. Estonian banks require a certified appraisal under the EVS 875 standard — produced by a licensed hindamisekspert after an on-site visit — as mandatory collateral documentation for mortgage lending.
Use Estiq's AVM for: pricing strategy, market research, buyer offer benchmarking, broker presentations, and portfolio monitoring. Use an EVS 875 appraisal for: bank mortgage collateral, legal disputes, insurance, and official valuations.
2. Data sources
Estiq draws from seven primary data sources. All transaction data comes from official Estonian state registries — no user-submitted or portal-sourced prices are used in the core AVM.
| Source | Data used | Update | Role in AVM |
|---|---|---|---|
| Maa- ja ruumiamet, tehingute andmebaas Maa- ja ruumiamet, tehingute andmebaas (tehingute andmebaas) |
Notarised transaction prices — buyer/seller-agreed prices on all Estonian residential property sales | Monthly | Primary price signal. All comparable sales are drawn exclusively from this register. |
| Ehitisregister (EHR) National Building Register |
Building specifications: construction year, floor count, building type, total area, kasutusluba status | Weekly | Used to pre-fill form inputs and filter comparables by build year (±5 years). |
| MKM Energy Database Ministry of Climate |
Energy performance certificates — A through H class ratings for individual buildings | Weekly | Energy class coefficient applied as a valuation adjustment. A/B adds premium; F–H applies discount. |
| Uber H3 Spatial indexing |
Hexagonal geocell grid at resolution 9 (~0.1 km² per cell) covering all of Estonia | Daily | Distance weighting: transactions in the same H3 cell as the subject property receive 3× weight. |
| Statistikaamet Statistics Estonia |
Macro price indices: quarterly housing price index by county and property type | Weekly | Used to detect rapid market shifts and apply trend correction between data refresh cycles. |
| OpenStreetMap OSM Contributors |
Points of interest: schools, parks, transit stops, commercial zones, green space polygons | Weekly | Proximity signals fed into the Estiq Life Index. Not used in core price calculation. |
| Estonian Environmental Board Keskkonnaamet |
Air quality monitoring station data — AQI readings across Estonian cities | Daily | Feeds the Air Quality component of the Estiq Life Index™ displayed on district and address pages. |
Estiq's AVM is powered exclusively by notarised state registry transaction prices. Asking prices in property advertisements reflect seller expectations, not actual market outcomes — that is why Estiq draws only from Maa- ja ruumiamet, tehingute andmebaas records, which capture the prices buyers and sellers actually agreed upon.
3. AVM calculation — step by step
The model runs in real time when a user submits an address. The pipeline completes in under two seconds.
1. Address resolution and building matching
Source: EHR • ~50msThe input address is resolved against the Ehitisregister to identify the exact building record. Building attributes — construction year, floor count, total area, building type, and kasutusluba status — are retrieved and pre-filled. Apartment-level data is used where available to narrow the comparable pool.
2. Comparable transaction selection
12-month lookback • ±15% area • ±5yr build yearThe model queries the Maa- ja ruumiamet, tehingute andmebaas transaction database for sales matching the subject property within the last 12 months. Two hard filters are applied: area within ±15% of the subject property, and construction year within ±5 years. Transactions outside these bounds are excluded regardless of proximity.
3. H3 geocell proximity weighting
Same cell: 3× • Adjacent: 1.5× • Other: 1×Each qualifying comparable is assigned a spatial weight based on its distance from the subject property using the Uber H3 grid at resolution 9. Transactions in the same H3 cell as the subject property receive a weight of 3×. Transactions in adjacent cells receive 1.5×. All other qualifying transactions receive 1×.
4. Condition coefficient application
New: +12–18% • Excellent: +6–10% • Good: baseline • Fair: −5–8% • Needs Reno: −12–18%The user-reported condition of the property triggers a multiplicative coefficient. These coefficients are calibrated annually against Maa- ja ruumiamet, tehingute andmebaas paired sale data for properties before and after renovation in each major Estonian city.
5. Energy class adjustment
A: +8–14% • B: +3–6% • E-F: −4–8% • G-H: −10–18%The energy class from the MKM certificate database is applied as an additive adjustment to the price per m². Estonian buyers increasingly price energy efficiency into their offers, and this gap has widened since 2022 with rising heating costs. A-class properties command a meaningful premium over F–H class properties of the same size, age, and location.
6. Floor adjustment
Ground floor: −3–6% • Top floor (panel): −2–4% • Top floor (new): +2–5%Floor position within the building is applied as a minor adjustment. Ground floor units in Estonian panel buildings typically trade at a discount due to noise and security concerns. Top floor units may attract a premium (penthouse effect) or discount (roof maintenance, insulation), depending on building type and district.
7. Price range and confidence interval calculation
High: ±5–8% spread • Medium: ±10–14% spread • Low: ±18–25% spreadThe weighted median price per m² is calculated from the adjusted comparable set. The price range is produced by applying a confidence-based spread around this median. The confidence level is determined by the number of qualifying comparables: 10+ comparables produce a High confidence range (narrow spread); 4–9 produce Medium; fewer than 4 produce Low (wide spread).
4. Confidence intervals explained
The confidence level shown on every Estiq valuation reflects the strength of the comparable evidence behind it — not a general quality score.
High confidence
Strong comparable pool in the same or adjacent H3 cells. Price range is narrow (±5–8%). Typical in active Tallinn districts: Lasnamäe, Mustamäe, Kesklinn, Kristiine.
Medium confidence
Adequate comparable pool, moderate spread (±10–14%). Common in smaller cities (Tartu, Pärnu) and less active Tallinn sub-districts. Consider consulting a broker for final pricing.
Low confidence
Thin data — atypical property type, rural location, or very low transaction volume. Wide spread (±18–25%). Use as a starting point only; broker or EVS 875 appraisal strongly recommended.
5. Estiq Life Index™
The Estiq Life Index is displayed on all district, neighbourhood, and address pages. It is a composite quality-of-living score calculated per 1 km² grid cell from four data streams:
🛡️ Crime Safety
Incident rate per 1 km² zone from Police and Border Guard Board open data. Scored 1–10, normalised against the Estonian national average.
💨 Air Quality (AQI)
Real-time AQI from Estonian Environmental Board monitoring stations, interpolated to 1 km² cells. Updated daily.
👥 Population Density
Residents per 1 km² from Statistics Estonia. High density signals urban amenities; used for liveability scoring and walkability proxies.
🏫 Schools & Green Zones
Catchment quality from school performance data (akadeemiline reiting) plus green space polygon coverage from OpenStreetMap.
6. Limitations and what the AVM cannot see
While the model is highly accurate, it is important to know its boundaries:
- Physical condition: The model uses user-reported condition, not an on-site inspection. Unreported defects, structural issues, or undocumented renovation work are not captured.
- Legal encumbrances: Mortgages, easements, debt with the building management company (korteriühistu), and other legal constraints on the title are not reflected.
- Rental income and yield: The AVM produces a capital value estimate only. Rental yield analysis is not included.
- Renovation specifics: A full kitchen and bathroom renovation increases value beyond the "Excellent" condition coefficient, but specific renovation costs and outcomes are not modelled at the individual property level.
- Atypical properties: Heritage buildings, properties with significant plot value, commercial-residential mixed-use units, and properties with unusual configurations may be less accurately valued by the AVM.
7. Frequently asked questions
How accurate is Estiq's property valuation?
Estiq's AVM is based on 180,000+ notarised transactions from the Maa- ja ruumiamet, tehingute andmebaas (tehingute andmebaas). In areas with high transaction density — such as Lasnamäe, Mustamäe, and Kesklinn — the model achieves high confidence by drawing on 10 or more comparable sales within the same Uber H3 geocell. Accuracy is highest for standard apartments in active markets and lower for atypical properties or rural areas with fewer comparables. This is a statistical estimate, not a certified EVS 875 appraisal.
What data sources does Estiq use for property valuation?
Estiq uses seven primary data sources: Maa- ja ruumiamet, tehingute andmebaas (tehingute andmebaas) for notarised transaction prices, Ehitisregister (EHR) for building specifications, the MKM energy certificate database for A–H energy class data, Uber H3 for spatial geocell indexing, Statistics Estonia (Statistikaamet) for macro price indices, OpenStreetMap for proximity signals, and Estonian Environmental Board data for air quality inputs to the Estiq Life Index. All transaction data is updated monthly.
What is the difference between Estiq's AVM and an EVS 875 certified appraisal?
Estiq's automated valuation model (AVM) is a statistical tool for instant market price estimation. It uses verified transaction data but does not include a physical inspection of the property. An EVS 875 certified appraisal is a formal document produced by a licensed valuer (hindamisekspert) after an on-site visit. Estonian banks require EVS 875 appraisals as mandatory collateral documentation for mortgage lending. Estiq's AVM is suitable for market monitoring, pricing decisions, and broker briefings — not for bank collateral.
What does the confidence interval mean in Estiq's valuation?
Estiq's confidence intervals reflect how many comparable transactions back the valuation. High confidence means 10+ relevant sales in the same H3 geocell within 12 months — the price range is narrow and well-supported. Medium confidence (4–9 comparables) gives a slightly wider range. Low confidence (fewer than 4 comparables) indicates an unusual property type or low-transaction area; the range is wider and users are advised to also consult a broker or certified valuer.
How often is Estiq's property data updated?
Estiq's transaction database is updated monthly from the Maa- ja ruumiamet, tehingute andmebaas (tehingute andmebaas). Building data from Ehitisregister and energy certificate data from MKM are synchronised on a weekly basis. District-level market statistics — including median price per m², transaction volume, and 3-month trend indicators — are recalculated monthly after the new data import. This ensures that all valuations and district pages reflect the most current available market data.
Data attribution:
Try the AVM on your property
Free for any Estonian address. No login required. Results in under 2 seconds.