BorderRev · Model 2 of 5

The valuation that
finds market price.

BorderRev Valuation runs every declared value against real external market data — automatically, in under 3 seconds. WTO Methods 2, 3, and 6 in sequence. A confidence score so auditors know exactly how strong each finding is. Every declaration, every time.

valuation · req_4d8b92c undervalued 78%
Declared value $4,875 (25 units @ $195)
Market value $22,435 (FOB · Method 2)
WTO Method Method 2 — identical goods
Country of origin Vietnam ✓ matched
Obs. window 22 transactions · 90 days
Confidence 0.91
Risk UNDERVALUED 78%
Declared unit price ($195) is 78% below the median FOB transaction value ($897.40) for identical Samsung Galaxy S24 Ultra 256GB units from Vietnam, based on 22 verified import observations within the last 90 days.
22 import records Vietnam · same origin 90-day window
< 3s
Per-item valuation
2, 3 & 6
WTO methods applied
60–90%
Cache hit rate steady state
VIN
Vehicle decode + comps

Under-valuation is the invisible revenue drain.

An importer declares a container of electronics at $50,000. Market price is $180,000. Your valuation officer has 30 seconds per declaration. No external price database. No AI. Just experience and intuition.

Manual spot-checking catches fewer than 2% of under-declared consignments. A single importer fraudulently under-declaring high-value electronics over three years can cost a customs authority $50 million or more in lost duties and VAT.

The problem is not negligence — it is scale. No team of humans can run every declared value against current market data across hundreds of thousands of lines per day.

"Customs undervaluation costs developing economies an estimated 3–5% of GDP in lost revenue annually." — WTO Trade Facilitation Research, 2024
< 2%
of under-declarations caught by manual spot-checking
$50M+
revenue loss from a single systematic under-declarant over 3 years
BorderRev Valuation checks every declaration, every time — not a sample.

From declaration to market verdict.

A seven-stage pipeline turns a raw goods description into a WTO-compliant valuation verdict in under three seconds. Semantic caching means repeat items return instantly without re-running market retrieval.

Semantic Similarity

Local sentence-transformers (all-MiniLM-L6-v2) embed every goods description into a 384-dimensional vector. Near-duplicate items retrieve their cached valuation in milliseconds, bypassing market retrieval entirely.

Market Intelligence

Agentic retrieval pulls structured price data from exchange prices, manufacturer RRP, and verified marketplace sources. CSS selector extraction and Schema.org JSON-LD parsing produce reliable price observations without LLM hallucination risk.

WTO-Compliant Verdict

Prices are normalised to FOB via incoterm conversion tables keyed on origin country, commodity chapter, and transport mode. WTO Methods 2, 3, and 6 are applied in sequence, with the result scored for confidence and returned with full source attribution.

Every verdict shows its working.

valuation · req_4d8b92c — 2026-05-24
Declaration Description : "Samsung Galaxy S24 Ultra 256GB Titanium Black" Declared : $4,875.00 for 25 units ($195.00 each) HS Code : 8517.13.00 Origin : Vietnam (Samsung Electronics Vietnam Co.) Method Selection — WTO Customs Valuation Agreement Art. VII Method 1 : Rejected — related-party transaction suspected Method 2 : APPLIED — identical goods · same country of origin · within 90 days Method 2 — Identical Goods Search Goods : Samsung Galaxy S24 Ultra 256GB (all specs identical) Country : Vietnam ✓ — observations restricted to same country of origin Window : 2026-02-23 → 2026-05-24 (90 days) ✓ Observations: 22 verified import transactions Price range : $851.00 – $941.00 per unit (FOB) Median FOB : $897.40 per unit Valuation Verdict WTO Method : Method 2 — Transaction value of identical goods Incoterm : FOB (no adjustment required — terms matched) Market Price: $897.40 per unit Total Market: $22,435.00 for 25 units Risk : UNDERVALUED 78% Confidence : 0.91 Sources : 22 observations (verified import records · 3× licensed brokers) Finding : Declared unit price ($195.00) is 78% below the median FOB transaction value for identical goods from the same country of origin (Vietnam), imported within 90 days. Consistent with systematic under-declaration on this trade corridor.

Confidence scores drive triage.

The composite confidence score maps directly to downstream action queues. No manual sorting — every valuation verdict routes itself to the right team automatically.

High · Undervalued

Priority recovery queue

Immediate post-clearance recovery action or goods hold. Strong market evidence, clear methodology, defensible in a tribunal.

High · Accurate

Auto-accept

Declared value is within tolerance of market price. Result is cached so the same consignment is never re-valued needlessly.

Medium · Undervalued

Standard audit queue

Risk-scored alongside other signals — classification disputes, origin flags, trader compliance history.

Low confidence

Specialist review

Specialist valuations officer assigned, with full case context and source data. Decision written back to the knowledge graph.

01 · WTO-COMPLIANT BY DESIGN

Auditable, defensible, and grounded in treaty law.

Every valuation verdict cites the WTO method applied, the source tier used, the incoterm conversion applied, and the observations underpinning the price. When a finding is challenged in a customs appeal, the legal basis is already documented.

The system applies WTO Methods in strict hierarchical order. Method 2 — transaction value of identical goods — is always attempted first. For an observation to qualify under Method 2, three conditions must all be met: the goods must be identical in all respects; they must originate from the same country of origin; and they must have been imported within the last 90 days. Country of origin is not inferred from the goods description alone — it is matched explicitly against the country declared on each reference transaction. If fewer than three qualifying observations exist, Method 3 (similar goods, same criteria) is applied. Method 6 (fall-back deductive or computed value) is the final resort, with full computation trace.

Method 2 · Identical goods Method 3 · Similar goods Method 6 · Fall-back Incoterm normalisation
M2
Identical goods
Three criteria must be satisfied: (1) identical goods in all respects — same description, specification, and brand; (2) from the same country of origin; (3) imported within the last 90 days. All three must match for an observation to qualify. Highest accuracy — the preferred method.
↓ if fewer than 3 qualifying identical observations
M3
Similar goods
Closely resembling, functionally interchangeable goods — same country of origin, within 90 days. Applied when Method 2 identical observations are sparse.
↓ if insufficient comparable goods
M6
Fall-back value
Deductive (retail minus duties, transport, profit) or computed from production costs. Full trace retained.
02 · VEHICLE INTELLIGENCE

VIN decoded. Exact spec. Market comps. Depreciation model.

Vehicles are among the highest-value and most commonly under-valued goods at the border. A 2022 BMW X5 declared at $15,000. Actual market value: $62,000. Without the VIN, that is almost impossible to catch in 30 seconds.

BorderRev Valuation decodes the ISO 3779 VIN automatically — World Manufacturer Identifier, Vehicle Descriptor Section, Vehicle Identifier Section — through the NHTSA decode API. Make, model, year, engine, trim, and country of manufacture are extracted and matched to market comparables. A depreciation model factors in age, mileage estimate, and salvage or rebuild status.

ISO 3779 VIN decode NHTSA API Age + mileage depreciation Salvage detection
WBA 53AJ0 N0C12345
VIN
Manufacturer BMW AG · Germany
Model X5 xDrive40i
Model year 2022
Engine 3.0L Turbocharged I6
Declared value $15,000
Market comps (FOB) $57,400 – $64,200
Depreciated market $62,100
UNDERVALUED 76% — Priority recovery queue
03 · SEMANTIC CACHING

The system remembers. Every repeat item returns instantly.

Once BorderRev Valuation has priced "iPhone 15 Pro Max 256GB Space Black", the next declaration of the same item — in any phrasing, any capitalisation — is matched semantically and returned from cache in milliseconds. No market retrieval, no web scraping, no API call.

Semantic similarity uses local sentence-transformers embeddings (all-MiniLM-L6-v2, 384 dimensions, CPU-only). In steady state, 60–90% of incoming declarations match an existing cache entry — meaning the marginal cost of a valuation approaches zero as volume grows.

all-MiniLM-L6-v2 384-dim embeddings pgvector similarity Redis hot cache
90% 60% 20% 0% target range Trial Month 3 Month 9 Steady state 60–90%
Cache hit rate over time — most valuations eventually cost near zero
04 · ZERO-COST AI

No paid API calls in normal operation.

For cash-constrained customs authorities — which describes most of the world — the economics matter as much as the capability. BorderRev Valuation is designed to operate without paid LLM APIs in its standard path.

Rule-based keyword extraction and NLP heuristics handle the majority of product descriptions. Structured HTML extraction (CSS selectors, Schema.org JSON-LD) pulls price data reliably from market sources without LLM inference. Google Gemini Flash on free tier handles genuinely complex or ambiguous descriptions as a fallback, degrading gracefully if the free quota is exhausted. Local sentence-transformers run on CPU with no GPU required.

Rule-based extraction Gemini Flash · free tier Schema.org JSON-LD CPU-only · no GPU
Rule-based NLP
Keyword dictionaries + regex. Primary path, zero cost.
Local embeddings
all-MiniLM-L6-v2, ~80MB, CPU-only. No cloud dependency.
HTML extraction
Schema.org JSON-LD + CSS selectors. More reliable than LLM.
Gemini Flash
Free-tier only. Edge cases and complex descriptions. Optional.

Ready to see it on your declarations?

We offer a short, no-risk trial against a sample of your historical declarations. We return valuation verdicts with confidence scores and source attribution — you keep the findings. No long engagement, no procurement overhead.

Arrange a no-risk trial Back to BorderRev