What is an AVM, exactly?
An Automated Valuation Model is a statistical model that estimates a property's market value based on comparable transactions, property characteristics (floor area, year built, type) and environmental factors. Classic AVMs use hedonic regression, while modern variants use gradient boosting (XGBoost, LightGBM) and computer vision features from facade or aerial imagery. An AVM does not replace an appraiser, but it is a tool for scalable valuation, portfolio-wide revaluation and ongoing monitoring. In the Netherlands most people know the concept through Calcasa values or the WOZ-style estimates on property marketplaces; commercial applications are broader.
How accurate is AI property valuation compared with an appraiser?
For standard properties in standard neighbourhoods, a well-trained AVM comes close to the appraiser, usually within a few percent, comparable to the spread between two appraisers. For unusual properties (listed buildings, recreational property, offices with an unusual tenant, retail in shrinking areas) the spread widens and an appraiser is indispensable. Our models provide an explicit confidence score per valuation, so you know when you can rely on the model and when you need a physical appraisal. For supervisory purposes we also document feature importance per outcome, so that an unexpected valuation remains explainable.
Will AI replace my appraisers, or is it a supplement?
A supplement. AVMs and CV pipelines scale valuation and inspection to volumes that are not feasible by hand, for example portfolio-wide revaluation or roof inventory across a thousand properties. For complex individual appraisals, legal reporting and disputes, a NRVT or RICS appraiser remains in charge. We usually see the appraisal team move up the value chain into review, complex casework and advisory work. The NRVT and the RICS Red Book explicitly allow AVMs as a supporting tool, provided the methodology and limitations are documented, which we deliver as standard.
Can you integrate with BAG, Kadaster and RVO?
Yes, that's a standard part of our stack. We work with BAG (property characteristics), Kadaster (BRK ownership and transaction history), BGT (geometry), BRT (topography) and the RVO energy label database. For commercial property AVM data, we also integrate with Brainbay, Calcasa or Altum AI. You handle the subscription yourself; we build the pipeline. For climate risk features, we also use the Klimaateffectatlas and, depending on scope, flood or subsidence data from the water board or TNO.
What does the EU AI Act mean for our AVM?
An AVM that helps decide on a consumer mortgage falls under Annex III of the AI Act and is classed as high-risk. That brings requirements around data governance, bias monitoring, technical documentation, human oversight and transparency towards the end user. For commercial property AVMs (B2B) the bar is lower, but the same principles are good practice. We include an AI Act compliance pack as standard; see also our page on
custom LLM integrations for the wider context.
Do you work with drone and satellite data?
Yes. For roof condition, solar panel inventory and maintenance planning, we use drone imagery combined with aerial photo archives (Cyclomedia, Beeldmateriaal Nederland) and, for large-scale projects, satellite data (Sentinel, Planet). For street and facade analysis, we use public streetview data and BAG integration. The computer vision pipeline is largely reusable across clients: training the detectors for roof tile condition, moss growth, solar panels and skylight types is a one-off effort, and deploying it across a portfolio is a matter of configuration.
Could we build a tenant or buyer portal with AI-powered Q&A?
Yes. A customer portal with retrieval-augmented generation over your tenancy agreements, service documents and owners' association papers is a popular follow-on to an AVM project. We build it to the same compliance standards as the valuation tools: audit logging, human escalation, and clear boundaries on what the model may and may not comment on. For housing associations with large tenant volumes, this is often the most visible AI product to the outside world, while AVM and computer vision do the heavier lifting internally.
What determines the cost of a property AI project?
Mainly: the quality and volume of your own data, the number and complexity of integrations (BAG, Kadaster, RVO, Brainbay or your own acquisition system), explainability and compliance requirements (EU AI Act, NRVT), and whether we build an MVP AVM or a full platform with a portal and monitoring. After the data audit, we give you a concrete estimate for the entire build, not an open-ended one. We work in sprints, and each sprint delivers something working, so you can steer on scope earlier than on budget.
Do you sell a product or build custom?
Custom. We are not an AVM vendor like Brainbay or Calcasa — we build for your organisation, on your data, with your methodology. That also means the model and the codebase are yours, not ours. For components we come across more often (BAG/Kadaster connectors, RVO pipeline, basic CV detectors) we do use reusable building blocks, but these are under an open licence so you do not have to depend on us for further development.
