AI Hotel Ranking
Methodology & disclosures
We publish placement percentages and positions on the boards; the sample sizes and confidence behind them live here. Everything is re-derivable from the same raw answers.
How a placement is measured
We ask an AI engine the questions travelers actually ask — no hotel or brand names in the prompts — and record which hotels it names and how it ranks them.
A hotel’s placement ratefor a board is the share of that board’s eligible answers in which the engine names the hotel. The overall board uses citywide questions (“best hotels in New York”); each neighborhood board uses that area’s questions. A hotel appears on a board because the engine names it there — not because of any tag we assign.
Each question is asked several times to average out run-to-run variation. We keep two signals separate and never merge them into one score: how often a hotel is named (the ranking) and what sources the engine cites (the sources board).
Sample size & confidence
We show percentages, not raw counts — but every percentage carries a sample size and a confidence interval underneath.
Wilson 95% score intervals on each placement rate (n = the board's eligible answers). Repeats cluster by prompt, so intervals are approximate.
Boards range from 6 to 24 answers (median 12); the overall board uses 88. Boards with fewer than 12 eligible answers are withheld as too small to publish (1 withheld this run).
What we exclude
A ranking is only as trustworthy as what it leaves out.
- Blind-validation hold-out hotels (reserved to validate the method — never ranked)
- Sigtrip customers (conflict of interest — recorded, never placed)
- Closed hotels
- Segments with fewer than 12 eligible answers (sample too small)
Conflict of interest & corrections
Sigtrip sells AI-visibility tools to hotels, including some that appear in this market. To keep the ranking honest, a hotel’s status as a Sigtrip customer never affects its placement — customers are recorded and excluded from the boards, and a separate set of hotels is held out entirely to validate the method.
These figures are a snapshot of what an AI engine said at a point in time, not a judgment of any hotel. If something looks wrong, tell us and we’ll review it against the underlying answers: hello@sigtrip.com.
Sigtrip AI Hotel Ranking — our own ChatGPT runs, from our own census and product experience. Percentages are placement rates over eligible answers.