AVMs for a Proportional Property Tax

An AVM estimates property values using historical transactions, property attributes, and location data. In taxation, AVMs operate within mass appraisal systems (IAAO, 2017) applying consistent methods across entire jurisdictions with ongoing statistical validation.

For a proportional tax, the AVM must produce a point estimate of each property's capital value, not just assign it to a band. Two broad model classes are used:

What matters is the overall system, not any single model: data collection, regular revaluations, quality checks, and a credible appeals process.

Regression vs machine learning

Regression models remain common because their coefficients are transparent and legally defensible. ML models, especially gradient boosting, produce lower valuation error but are harder to explain at appeal. In practice, most jurisdictions layer ML on top of a regression baseline, gaining accuracy while retaining an interpretable core.

Spatial modelling

Location is the primary driver of value. Systems incorporate it through market zones, coordinate-based features, proximity and accessibility metrics, and environmental variables such as flood risk and noise. More advanced systems directly model spatial relationships rather than relying on crude zoning.

All mature tax valuation systems are hybrid, combining model outputs with human review. Human intervention focuses on outliers, unique properties, sales validation, and legal compliance. Even highly automated systems such as Cook County (Illinois) retain substantial manual validation.

The balance is itself a design choice: more automation delivers consistency and lower unit cost; more oversight catches errors the model cannot see and strengthens public legitimacy. A proportional tax in England would almost certainly follow this hybrid pattern.

Valuation frequency involves a three-way tension: fairness, cost, and political acceptability. Outdated valuations create inequities, but frequent updates mean more visible bill shifts, generating political resistance and higher appeal volumes.

England's Council Tax valuations date from 1991; a proportional replacement would need to establish a regular cycle from the outset.

The Netherlands offers perhaps the closest analogue to what a proportional property tax in England would require: annual capital-value assessments of the entire housing stock, centrally audited, with a mature appeals process.

Property valuation for tax is hard: properties are heterogeneous, prices vary sharply across space, attribute data is incomplete, and models risk systematic bias against particular areas or property types. Under a proportional tax, valuation accuracy directly determines how fairly the burden is shared.

Tax AVMs are evaluated using ratio studies (IAAO, 2013), not standard ML metrics:

Key risks include geographic or socio-economic bias, property-type mispricing, model drift, and data errors; the last of these is often more consequential than model choice.

A proportional tax would generate significantly more appeals than the current band system, because individual valuations create more grounds for dispute. Appeals serve a dual function: correcting errors and conferring legitimacy. But high volumes carry real administrative cost and create budget uncertainty for local authorities.

International experience shows that systems separating factual corrections (wrong floor area, missing extension) from valuation disputes (disagreement over market value) operate more efficiently (Almy, 2014). Designing the appeals process is as important as designing the model.

Data quality is the binding constraint. Three categories matter most:

Model reliability falls in low-liquidity segments such as rural areas, high-value properties, and unusual types; here the need for human review is greatest.

Transaction volumes

England has good transaction price coverage via HM Land Registry (1.0–1.2 million annual sales in normal conditions), though turnover is thin in rural areas and at the top of the market.

Transaction volumes would support modelling for mainstream properties. But an AVM also needs property attributes; size, type, condition, tenure; linked to each address. This is where England falls short. The feasibility question is less about sale prices and more about whether a reliable attribute dataset can be assembled.

Data availability

The Netherlands maintains a unified property register with standardised attributes linked to every address; no equivalent public dataset exists in England. However, the VOA maintains its own property records (dwelling type, area, age, bedrooms, bathrooms, parking, plot size). These are not publicly available but constitute a working attribute dataset, as the Welsh AVM demonstrates.

The VOA's Welsh AVM: a working precedent

The VOA has built and deployed an AVM for the 2028 Council Tax revaluation in Wales, covering 1.5 million properties. The model uses a Gaussian Markov Random Field to estimate continuous spatial variation, and was externally assured by the IAAO as "more than satisfactory".

The approach is explicitly "model assisted": the AVM generates first-pass valuations, then professional valuers review properties near band boundaries and those flagged as unreliable. The VOA estimates this reduces costs by roughly one-third versus purely manual valuation.

This demonstrates the VOA holds workable attribute data and has built the institutional capability for mass appraisal. The question is whether it can scale.

The Welsh AVM confirms the VOA can build a credible system from existing data. But it does not settle whether the same approach can deliver the accuracy needed for a proportional tax across a property stock 16 times larger and considerably more diverse.

A proportional tax could take several forms, each with different AVM requirements: