Technical Summary

UK Residential Automated Valuation Model

1. Model Overview

The Gadsden Valuations AVM produces point estimates of residential property market value for properties in England and Wales, consistent with the IVS 104 definition of Market Value.

For each property, the model produces:

  • A point estimate of market value (£) with upper and lower bounds
  • A confidence tier (1–3, or declined) with Forecast Standard Deviation mapped to the EAA common 0–7 scale
  • Comparable transactions supporting the estimate
  • Downloadable PDF report with full audit trail

1.1 Intended Use Cases

The AVM is designed for integration into lender valuation cascades. It operates as the first node in an AVM → desktop → physical inspection workflow, providing structured outputs with per-property confidence scoring. It is not intended as a standalone replacement for physical valuation where required by lender policy or regulation.

  • Portfolio revaluation for Basel 3.1 compliance (expected January 2027)
  • Remortgage AVM-assisted valuations where physical inspection is not proportionate
  • Independent cross-check against physical valuations or competing AVM outputs
  • Desktop review support for valuers conducting restricted-service assessments
  • Market monitoring for the 10% revaluation threshold

1.2 Coverage

England and Wales. Four standard residential property types: detached, semi-detached, terraced, and flats/maisonettes. The model does not cover Scotland, Northern Ireland, commercial property, new-build prior to first sale, or non-standard constructions.


2. Methodology

Gradient-boosted decision tree ensemble trained on Land Registry data enriched with government open data sources.

2.1 Validation Approach

All accuracy metrics use strict quarterly bulk test: the model is trained on transactions up to a cutoff date and tested exclusively on future transactions it has never seen. The current test set comprises 147,188 properties from the Q4-2025 bulk test. This prevents data leakage and ensures published figures reflect real-world predictive performance.

2.2 Benchmark Methodology

All accuracy metrics are measured against Land Registry completion prices — the actual amount paid in arm’s-length transactions. This is a materially harder test than benchmarking against surveyor opinion (which is itself an estimate with a ±5–10% margin against eventual sale prices).

The industry leader, Hometrack, reports ~80% PE10 benchmarked against surveyor valuations. A like-for-like comparison against actual sale prices would produce lower figures. Published PE10 figures from providers using the surveyor benchmark are not directly comparable with our figures.


3. Accuracy Metrics

Metric Value Industry Context
Median Absolute % Error (MdAPE)6.0%Single digits considered strong (Ecker 2020)
Within ±5% (PE5)43.3%
Within ±10% (PE10)69.4%Key lender evaluation metric
Within ±15% (PE15)82.7%
Within ±20% (PE20)89.4%
Median absolute error£17,250
Test set size147,188Q4-2025 bulk test

3.1 By Property Type

Type MdAPE PE10 PE15 PE20 N
Flat7.2%63%77%85%23,817
Terraced5.9%69%82%89%47,321
Semi-Detached5.6%72%85%91%43,907
Detached6.0%70%84%91%32,143

3.2 By Price Band

Price Band MdAPE PE10 N
<£150k9.3%53%21,652
£150-300k5.6%72%59,783
£300-500k5.3%75%43,719
£500k-1M6.3%69%20,176
£1M+10.0%50%1,858

4. Confidence Model

Each valuation receives a confidence tier based on data availability and comparability factors. This satisfies the IVS 105 requirement for accuracy measures and the EAA ESSVM requirement for a per-property confidence score translatable to Forecast Standard Deviation.

Tier Confidence Typical Profile Recommended Action
1 (High)EAA 0–2Dense comparables, known floor area, common typeAccept for valuer review
2 (Medium)EAA 3–4Some comparables, partial data, less common typeDesktop review recommended
3 (Low)EAA 5–6Sparse comparables, missing key data, unusual propertyPhysical inspection required
DeclinedEAA 7Insufficient data for meaningful valuationCannot value

Confidence can be upgraded by the client. The most impactful upgrade is provision of an EPC (£60–120), which supplies floor area, construction age, and energy characteristics — typically sufficient to move a property from Tier 2 to Tier 1. This creates a practical path to maximise high-confidence coverage without sacrificing accuracy.


5. Known Limitations

The model values properties based on recorded data. It cannot account for:

  • Internal condition — renovation status, kitchen/bathroom quality, structural issues. This is the primary limitation of any AVM and the principal reason physical inspection remains necessary for higher-risk lending decisions.
  • Bespoke improvements — extensions or conversions not yet reflected in EPC or planning data
  • Legal encumbrances — restrictive covenants, rights of way, leasehold complications beyond Land Registry data
  • Micro-location — specific view, aspect, noise, or neighbourhood factors a local agent would consider
  • Market lag — Land Registry data lags completion by 2–4 months

The confidence model flags properties where unobserved factors are more likely to affect accuracy.


6. Data Sources

Source Update Frequency Licence
HM Land Registry Price PaidMonthlyOGL v3
EPC RegisterMonthlyOGL v3
ONS Census 2021DecennialOGL v3
ONS House Price IndexMonthlyOGL v3
GIAS School RegisterDailyOGL v3
Ofsted Inspection RatingsRollingOGL v3
Environment AgencyAnnualOGL v3

All data sourced under Open Government Licence v3. No proprietary datasets.


7. Regulatory Alignment

PRA SS1/23 (Model Risk Management)

Documentation structured to support vendor model assessment by regulated firms. Published methodology, accuracy monitoring, confidence indicators, and per-valuation audit trail.

Basel 3.1 (expected January 2027)

Portfolio revaluation capability for capital adequacy compliance. 10% threshold monitoring. Batch and API delivery for scalable portfolio coverage.

IVS 105 (Valuation Models), sections 30–50

Model characteristics documentation, validation methodology, limitation acknowledgement.

EAA ESSVM 3rd Edition (2022)

Methodology disclosure, confidence scoring on common 0–7 scale, segmented accuracy reporting.

RICS Red Book Global Standards (January 2025)

Consistent with PS 1.3 (statistical valuation), PS 1.6 (AVMs), and VPS 5 (valuation models) disclosure requirements.


8. Further Information

Further technical detail is available on request to organisations conducting vendor due diligence.

A sample valuation report is available at gadsdenvaluations.com/sample-report.

Contact: sales@gadsdenvaluations.comgadsdenvaluations.com

Download this document

Get a branded PDF version of this technical summary.

Download PDF

Further technical detail

Available on request to organisations conducting vendor due diligence.

Contact sales@gadsdenvaluations.com

This document is for informational purposes. AVM outputs are statistical estimates, not formal valuations. Where regulation or contract requires a written valuation, independent professional review is necessary.

This site uses essential cookies and Google Analytics. See our Privacy Policy.