Technical Summary

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 per-property Forecast Standard Deviation mapped to the Fitch A–D classification bands and the EAA common 0–7 scale (or a no-value response)
• 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 295,026 properties from the H2-2025 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

3.1 By Property Type

3.2 By Price Band

---

4. Confidence Model

Each valuation receives a per-property Forecast Standard Deviation (FSD) from a granular lookup (confidence decile × property type × price band), mapped to the Fitch RMBS classification bands. This satisfies the IVS 105 requirement for accuracy measures and the EAA ESSVM requirement for a per-property confidence score expressed as Forecast Standard Deviation.

Properties with insufficient data are returned as a no-value response rather than valued with false confidence. An EAA 0–7 confidence level, derived from the same FSD, is included on every response.

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 lower the FSD and move a property into a stronger band. This creates a practical path to maximise coverage in the lower-FSD bands 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

The model rests on UK public-sector open data — HM Land Registry Price Paid (the training target), the Energy Performance Certificate register, and official open datasets covering schools, crime, flood risk, transport and demographics.

---

7. How Our Documentation Serves Lender Obligations

---

8. Further Information

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

Sample valuation reports are available at gadsdenvaluations.com/downloads.

Contact: sales@gadsdenvaluations.com • 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.