Industry field guide
Event ticket reservation, transfer and price records for AI
A ticket agency can test whether a model keeps the displayed price, reservation status and transfer events distinct.
- 2022 NAICS
- 561599
- Practice pack
- Example and answer key (JSON)
- Updated
What this guide tests
Which transfer is documented as accepted, which price belongs to R1, and what refund state can be reported?
See the specimen and fields · Work through the fictional records
Task and source context
A ticket agency can test whether a model keeps the displayed price, reservation status and transfer events distinct. The FTC’s unfair or deceptive fees guidance covers live-event tickets. That guidance provides context for building fictional price displays while keeping the exercise focused on data interpretation. FTC fees rule FAQs
Invent a reservation with a stated total and a later transfer invitation. Provide an acceptance event for one ticket and only the invitation for a second. Include a price document that belongs to a different reservation. Ask which transfers completed and which price evidence attaches to each reservation. Leave refund status unresolved unless a matching record establishes it.
Use original interface mockups and inert references. Exclude scannable tickets, real customer data and partner pricing systems. Secure rights for any third-party event art.
Industry research
The U.S. Census Bureau’s industry definitions establish which activities these codes cover. The workflow sources in this guide describe the task or record type. Fiund’s pilot below uses fictional material to test a specific decision within that scope.
561599 · All Other Travel Arrangement and Reservation Services
This U.S. industry comprises establishments (except travel agencies, tour operators, and convention and visitors bureaus) primarily engaged in providing travel arrangement and reservation services.
Build a pilot sample
Set up this pilot
Make mock event tickets with one transfer invitation and one acceptance. Change a separate ticket’s price and add a pending refund. Grade exact ticket and event state.
Prepare the test packets
- Start with the worked case. Use the fictional record types below as a guide to the source files you need. Give each packet a stable ID and save its source versions with it.
- Change one fact. Make one packet with enough evidence to answer the question and one where the evidence points to a different answer. Keep the other fields fixed so a reviewer can tell what changed.
- Remove the decisive evidence. Give the reviewer a third packet with a plausible near-match in its place. Have them write what can still be established and what evidence would resolve the rest.
Fields the reviewer needs
- Reservation and ticket reference
- Defines event scope.
- Stated price source
- Preserves the matching total.
- Invitation, acceptance and refund event type
- Separates stages.
Use Build an AI evaluation sample for service handoffs to turn the specimen into a brief with a defined task, source and review owner.
Fictional exercise
A transfer invitation and its acceptance apply to individual tickets
An original ticket-agency mockup uses inert references and no event art, scannable code, customer or transaction. Prices are invented document fields.
| Record ID | Source | What it records |
|---|---|---|
| TK1 | Reservation R1 | Two dummy tickets A and B; stated total 80 practice units. Original price card explicitly names R1. |
| TK2 | Transfer events | Invitations sent for A and B. Acceptance event explicitly references R1/A only; no B acceptance supplied. |
| TK3 | Other price and refund note | Price card for R2 shows total 70. Refund request names R1/B but no approval, settlement or completed refund event. |
Question for the model. Which transfer is documented as accepted, which price belongs to R1, and what refund state can be reported?
Show the reference answer
TK2 supports acceptance of R1/A's transfer and only an invitation for R1/B. TK1 provides R1's stated 80-unit total; TK3's 70 belongs to R2 and cannot replace it. TK3 records a B refund request without settlement evidence, so the refund remains requested rather than completed. Keep ticket-level transfers, reservation-level price and refund workflow separate without making a legal entitlement or actual payment conclusion.
How to check the result
Ask for the answer, the record IDs that support it and any fact the evidence leaves unresolved. Have a reviewer compare the response against the reference before deciding whether the sample is ready to expand.
Errors to flag in this case
- Treating all invitations as accepted because one ticket has an acceptance.
- Using another reservation's price or promoting a refund request to completed reimbursement.
Change the inputs and run it again
Add an acceptance for R2/B. Require R1/B to remain pending despite the same local ticket letter.
Score the decision and the evidence separately
Save the reviewer’s expected answer, supporting record IDs and unresolved fields in a separate answer key. Score the model on the decision, its citations and its handling of the deliberate gap. A correct answer citing a different case counts as an evidence error.
Before expanding collection, have a second reviewer run the same checks on the held-out packet. Keep related versions, views and exports of the same case together so they stay on one side of the training and evaluation split.
Check permission and scope
Use original interfaces and nonfunctional references. Exclude real tickets, customer data and partner pricing systems; clear third-party artwork separately.
Use approved or fictional service records. Exclude customer and worker data, site access details and sensitive surveillance material.
Describe an authorized archive through Fiund’s existing-data assessment, or describe a new capture capability through the collection brief. The contributor agreement covers the terms for participation.
Sources and further reading
Resources for this workflow
Company and program reviews
Use these reviews to compare sourcing, capture or evaluation approaches. Confirm the applicable program, accepted sources and terms with the provider.
Compare the approach
micro1 review for experts, trade footage and company data
Compare the prerequisites for an approved recording project before planning a contribution.
Compare the approach
Sama review for computer-vision labeling and model evaluation
Review labeling scope for visual state and exception checks in staged footage.
Related industry examples
Industry guide · NAICS 561510
Travel agency ticketing and itinerary status records for AI
Travel records can include a priced itinerary, an issued ticket and a later refund event.
Industry guide · NAICS 561431
Private mailbox center parcel receipt and pickup data for AI
A carrier status that says delivered may show receipt at a private mail center while the item is still awaiting collection.
Industry guide · NAICS 561520
Tour operator package changes and itinerary evidence for AI
Tour operators bundle transport, lodging or activities and may need to track changes at the component level.