Auction

What is Auction?

The number that decides whether an auction purchase makes sense is not the hammer price — it is the hammer price plus buyer's premium, fees, shipping and tax, compared against what similar lots actually sold for. Auction normalises live auctions, timed auctions and marketplaces into one model, values lots against comparable sales you can open and inspect, and computes the landed cost. Bidding, authorisation and money movement are governed by a deterministic policy engine rather than by a model.

Problems it solves

• Find lots across auction houses and marketplaces at once
• Compute buyer's premium, fees, shipping and tax into one landed cost
• Value a lot against comparable sales you can open
• Plan a maximum bid from cost and value rather than instinct
• Decide what to sell and where
• Keep bidding authorisation deterministic

Key capabilities

Comparable Valuation

Value something against comparable sales you can open and inspect.

All-In Cost Modelling

Compute the real landed cost behind a headline price — fees, premium, shipping, tax.

Market Screening

Filter a universe of instruments or lots down to those matching stated criteria.

Deterministic Policy Engine

Rules, not inference, decide what is allowed to proceed — so a model can advise and never authorise.

Evidence Trail

Every figure carries the record it came from, so a reader can check the answer instead of trusting it.

How it is built

One model across venues

Live auctions, timed auctions and marketplaces normalise into the same structure.

Inspectable comparables

A valuation opens onto the sales that produced it.

Landed cost

Premium, fees, shipping and tax computed into the number that matters.

Policy-governed bidding

A deterministic engine controls authorisation and money movement, not a model.

How it works

How the work is structured, and what each step's output rests on.

1. 1

   Normalise venues

   Source

   Bring auctions and marketplaces into one lot model.

2. 2

   Discover lots

   Observed

   Find lots matching stated interests across venues.

3. 3

   Value against comparables

   Estimate

   Price the lot against similar completed sales.

4. 4

   Compute landed cost

   Observed

   Add premium, fees, shipping and tax.

5. 5

   Apply bidding policy

   Source

   The deterministic engine governs authorisation and limits.

Example use cases

Each example has its own page you can read and share.

Ask Auction

Illustrative examples. Results depend on your own data.

• “What will this lot actually cost me delivered?”
• “What have comparable lots sold for this year?”
• “What is my maximum sensible bid here?”
• “Which venue should I sell this through?”

Security, governance and human control

Where the software deliberately limits itself.

Questions

Does it bid for me?

Bidding, authorisation and money movement are governed by a deterministic policy engine you configure. An inference never authorises a bid.

Where do comparables come from?

Completed sales, which you can open and inspect. A valuation you cannot check is a guess with a decimal point.