Aarhus RE Scanner: Automated Property Valuation Model
A solo-built automated valuation model (AVM) for Aarhus residential real estate, benchmarked directly against the accuracy figures published by the Danish tax authority's own model-development process, the one at the center of Denmark's 2013 ejendomsvurderingsskandale. Five reverse-engineered and public data sources feed a 5-model stacking ensemble, validated on a strict temporal holdout so the reported accuracy reflects genuine forward-looking generalization, not a favorable random split.
Base Models
5
Hit Rate (±20%)
82.2%
Data Sources
5
Holdout Test Rows
6,458
The Model
A hedonic log-price model: 5 base learners (Ridge, ElasticNet, LightGBM, XGBoost, CatBoost) combined via a Ridge meta-learner trained on out-of-fold predictions. Data is joined from Datafordeler BBR (structural attributes), OSM Overpass (spatial amenities), Statistics Denmark (macro/fiscal context), and two undocumented sources reverse-engineered from scratch: a historical sale-price API and an energy-certificate lookup, neither of which has an official public endpoint.
Validation is a single temporal holdout: every model is trained only on transactions before 2025-04-18 (~114,600 rows) and tested only on the ~6,458 transactions after that date, never seen during training or tuning, the same discipline used across every project on this site. A/B feature and architecture experiments are accepted only when they improve the net holdout RMSE summed across all three property segments (condo, house, apartment), no per-segment cherry-picking.
Benchmarked Against the Government's Own Model Development
Denmark suspended its public property valuations in 2013 after a damning Rigsrevisionen audit and spent the following years building a statistical replacement, documented in a 2014 expert-committee report (Engberg-udvalget) and a 2016 refinement (Skatteministeriet / ICE). Both publish the accuracy metric Danish valuation law actually targets: the percentage of assessments landing within ±20% of the real sale price. Pulled directly from both primary-source PDFs and compared against this model's own genuine held-out test predictions:
| Property type | SKAT, old system (2014) | Engberg prototype (2014) | ICE refined (2016) | Vurdst. production (2024) | This model (2026) |
|---|---|---|---|---|---|
| Houses | 62.9% | 67.5% | ~71% | ~80% (parcelhuse+rækkehuse blend) | 81.3% |
| Condos | N/A | 83.4% | ~85% | not published | 83.7% |
Vurderingsstyrelsen did publish real production-system accuracy for houses in June 2024 ("Høj træfsikkerhed i de nye ejendomsvurderinger"): ~81% within ±20% across ~500,000 2020-valuations (rising to ~82% with a 200,000 DKK bagatelgrænse), of which only ~12% had an actual sale to test against. That report covers parcelhuse and rækkehuse only; it does not cover condos (ejerlejligheder) or commercial land, so the condo comparison above still rests on pre-launch 2014/2016 development-stage figures, with no published production-system number to benchmark against.
Try the Search
Loading snapshot…