Ideas paper · prepared for HVIA

NEVDIS Registration
Intelligence Engine

How one monthly data purchase becomes the industry's only month-by-month record of Australia's heavy vehicle fleet.

Prepared for  Todd Hacking, HVIA
Date  29 July 2026
Reference  PROP-2026-015
Section 1

Where this starts

Thanks for the call, Todd. As promised, this is ideas rather than War and Peace: what we heard, where we push back on the standard pitch, and the solution we build instead. Scope, timeline and pricing come after we have seen one real extract.

Snapshot · what we heard
  • The goal: a monthly HVIA report on new truck and trailer registrations, split by weight class, manufacturer and axle configuration.
  • The source: the NEVDIS extract purchased through Austroads. Manufacturer, vehicle type, GVM, axles and more.
  • The problem: manual entry at eight state registries makes the data dirty. Kenworth is a K in Victoria and a KW in Queensland.
  • The catch: NEVDIS keeps no history. You can only ever buy the whole database as of right now.
  • The field: other vendors propose a data lakehouse with hand-built logic layers and an LLM front end. You asked for a better way if we have one.
Our thesis

Because NEVDIS only ever sells now, whoever banks each monthly snapshot ends up owning something Austroads itself does not offer: a month-by-month history of the national heavy vehicle fleet. That history is not for sale at any price. Bank it from day one and, twelve months in, HVIA holds a dataset nobody else in the industry can reproduce. This is a moat, not just a report.

NEVDIS / AUSTROADS · NO MEMORY MARoverwritten APRoverwritten MAYoverwritten JUNoverwritten JULthe only snapshotNEVDIS can sell THE PROBLEM NEVDIS keeps no historical records. No last month. No yesterday. Month-on-month change does not exist until someone builds it. captured and banked the day it lands HVIA HISTORY BANK · BUILT AND OWNED BY HVIA MARbanked ✓ APRbanked ✓ MAYbanked ✓ JUNbanked ✓ JULbanked ✓ + every month after, forever _ compounding while competitors start from zero THE MOAT Twelve months in, HVIA holds the only month-by-month record of Australia's heavy vehicle fleet. History is not for sale, so nobody can buy a copy later. Every month you wait is history lost for good. NEVDIS forgets. HVIA remembers.
Diagram 1 · the history bank: why starting soon matters more than starting perfectly
Section 2

Playing devil's advocate

You asked for our honest view of the approach on the table. Here it is, applied to the other vendors' pitch and to our own first instincts.

A lakehouse is the wrong size

Lakehouses are enterprise plumbing designed for petabyte-scale streaming data from many sources. HVIA has one authoritative source arriving once a month. Build a lakehouse and you pay enterprise complexity, and enterprise invoices, forever, for a job a lean cloud warehouse does in weeks. The architecture should fit the data, not the fashion.

Counting rows is not the hard part. Identity is.

A new VIN in this month's snapshot is not automatically a new truck sold. It can be a re-registration, an interstate transfer or an import returning to the register. A report that cannot tell the difference inflates the market, and the first manufacturer whose own sales figures disagree says so publicly. The fix is VIN-level differencing plus classification, shown in Diagram 3.

An LLM front end on dirty data is confident nonsense

The other pitch leads with the chat interface. We put AI where it earns its keep: entity matching inside the cleansing engine. Everything else is deterministic automation, which is cheaper, faster and auditable. As we said on the call, not everything needs AI. A conversational layer is a genuinely good later add-on, grounded in a clean warehouse so it quotes real numbers.

Three things no pitch deck mentions
  • Month one has no baseline. The first change report lands in month two, so the first extract should be bought and banked as early as possible. Every month of delay is history lost for good.
  • Licence terms decide the product. What Austroads permits HVIA to publish to members, and to media, needs confirming before the build, not after.
  • Nobody knows how dirty the data really is. One real extract and one day of audit answers it, and that should happen before anyone quotes a fixed price.
Section 3

The better way: a Registration Intelligence Engine

Four right-sized layers, fully automated end to end. Once live, the monthly report builds itself; a human touches it only to approve it before it goes to members.

NEVDIS extract full national snapshot monthly, via Austroads Broker API per-VIN spot checks for the genuinely ambiguous 1 Ingest & Archive • collects each extract on arrival • validates and fingerprints it • banks the raw snapshot forever ZERO MANUAL HANDLING the history moat starts day one 2 Cleansing Engine • rules for every known alias • AI matching for new variants • 30-second human review queue SELF-LEARNING the dictionary compounds monthly 3 History Warehouse • every cleansed snapshot stored • VIN-level month-on-month diff • new vs re-registered, classified VIN-LEVEL TRUTH immune to transfers muddying the counts 4 Report Factory • branded monthly PDF + web • league tables, trends, splits • plain-English commentary ONE CLICK, OR ZERO drafted by the engine, approved by a human spot-checks feed the cleanse · never bulk cost HVIA approves minutes, not days Members receive monthly report · live dashboard newsletter stats · media-ready figures A MONTH IN THE LIFE, ONCE LIVE Extract lands → archived → cleansed (auto + quick review) → VIN-diff computed → report drafted → HVIA approves → distributed. HVIA's hands-on time: minutes.
Diagram 2 · four provable components instead of an enterprise platform

Every component, including the raw archive, the alias dictionary and the warehouse, is built as an HVIA-owned asset: portable, documented and yours. Nothing is locked inside a vendor's platform.

Section 4

Month-on-month truth, at VIN level

The report's credibility rests on one question: was this vehicle genuinely registered for the first time this month? We answer it per VIN, never per total. As a bonus, VINs that leave the register give HVIA fleet attrition and fleet age insights that a simple count can never see.

JUNE SNAPSHOT 6ABZ…104 6KWD…771 6ISZ…918 6MCK…035 6VOL…562 6SCA…247 6 registered VINs JULY SNAPSHOT 6ABZ…104 6KWD…771 6ISZ…918 6MCK…035 6VOL…562 6KWD…882 6IVE…433 6FRT…690 8 registered VINs 5 CONTINUING same VIN both months still in the national fleet 3 NEW VINs never seen in any snapshot classified before counted: build year · first-seen · state history 1 EXITED VIN gone from the register fleet attrition insight, free 1 GENUINELY NEW REGISTRATION 2026 build, first time on any register. Counts in the monthly report and the manufacturer league table. 2 RE-REGISTRATIONS / TRANSFERS Older builds moving state or returning to the register. Excluded from new sales, tracked as fleet movement. THE PUNCHLINE A raw count says the market grew by 2. VIN-level classification says: only 1 new truck was actually sold. Credibility is the product here.
Diagram 3 · why we diff VINs, not counts
Section 5

Cleansing that compounds

Deterministic rules handle every alias already learned. AI proposes matches for new variants with a confidence score. Only the genuinely ambiguous reaches a person, who confirms in about thirty seconds, and the engine remembers that answer forever.

RAW MANUAL ENTRY K KW K'WORTH KENWORTH KEN WORTH one truck maker, five spellings ALIAS DICTIONARY deterministic rules, instant, free to run, fully auditable K = KW = K'WORTH = KENWORTH known alias? matched instantly (the vast majority) new variant? AI ENTITY MATCH "KENW0RTH" looks like KENWORTH proposes a match with a confidence score high confidence → auto-accept low confidence? REVIEW QUEUE a human confirms in about 30 seconds. Only the genuinely ambiguous ever reaches a person CANONICAL RECORD KENWORTH ✓ one name, every report, every month every answer is written back to the dictionary and remembered forever Month 1: the dictionary learns hundreds of variants. Month 12: almost nothing new left to learn. It compounds, and HVIA owns it.
Diagram 4 · a cleansing engine that gets smarter every month
Section 6

What lands in inboxes each month

One branded report, drafted by the engine and approved by HVIA in minutes:

New registrations by weight class4.5 to 8 tonne, 8 to 20 tonne, 20 tonne and above
Manufacturer league tablesunits, market share and movement against last month
Trailers by axle configurationplus truck versus trailer splits
State-by-state viewwhere the market is growing, and where it is not
Trend chartsricher every month as the history bank grows
Plain-English commentaryready for the newsletter, member comms and media releases
The asset behind the report

The report is the monthly deliverable. The asset is the history bank behind it: it grows every month and gets harder to compete with. Later, the same warehouse can power member benchmarking portals, anomaly alerts, forecasting, media-ready market stats and tiered data access for members and non-members. Each is a decision for another day, and none requires rework.

Section 7

How this starts

We de-risk before we build. Everything below firms up after one day with one real extract.

Day one
Data audit

One sample extract under NDA. We measure how dirty the data really is, confirm field coverage and confirm Austroads licence terms for publishing.

Weeks 1 to 4
Foundation

Ingestion, permanent archive, cleansing engine v1 and the first automated monthly report, end to end.

Weeks 5 to 8
Intelligence

History warehouse, VIN-level differencing and classification, live dashboard and automated distribution.

When ready
Extras

Member benchmarking, anomaly alerts and conversational analytics, once the foundation has earned trust.

No pricing in this paper, deliberately. We would rather show you real numbers from your real data than guess in a document.

Section 8

Next step

A 45-minute Google Meet to walk through these ideas and, ideally, look at a sample extract together. Connecting to databases, extracting and amalgamating data, cleansing it and producing automated reports is our bread and butter. We would love to build this with HVIA.

Ready when you are, Todd

One email locks in the Google Meet and we bring the whiteboard.

Lock in the Google Meet