Huxo Research · Vol. 01

How AI decides which hotel wins the answer

Original research on how ChatGPT, Gemini, Claude and others select hotels — the biases they carry, the features they weigh, and what independent hotels can do about it.

Published10 chapters
AI Models TestedChatGPT, Claude, Gemini
Markets Analyzed61
Last UpdatedApril 2026
All studies
Chapter 10 · Web Discovery

95.9% of hotels have no AI crawler rules

104,214 hotels parsed. 95.9% have zero AI-specific rules. Most hotels are open to AI crawlers by default — but not strategically.

Apr 30, 20266 min read
Chapter 09 · Web Discovery

Only 5.8% of hotel websites have llms.txt

104,214 hotels scanned. 5.8% adoption. Zero AI crawler requests in server logs. The honest state of llms.txt in hospitality.

Apr 22, 20267 min read
Chapter 08 · Geographic Context

Geographic context changes which hotel wins

A driving-times table prepended to a plain query reshapes ChatGPT’s recommendations — a case study on how context alters AI’s pick.

Apr 14, 20268 min read
Chapter 07 · Agent Bias

Agents inherit positional bias too

Claude, Gemini, and GPT agents tested via OpenCode and browser UIs. Even with tools, the top of the list wins.

Apr 5, 20269 min read
Chapter 06 · Mitigation

Fixing positional bias: what actually works

15 mitigation strategies tested head-to-head across 15,616 trials. Only one category of intervention actually worked.

Mar 28, 202611 min read
Chapter 05 · Human vs LLM

Would a human pick the same hotel?

We compared human travelers (conjoint literature) and AI models on the same decisions. The gaps reveal where AI helps — and where it quietly fails guests.

Mar 20, 20269 min read
Chapter 04 · Cross-Model

Each AI has a different taste

ChatGPT, Claude, Gemini — compared side-by-side. Which model favors brands, which favors independents, and why it matters for visibility strategy.

Mar 11, 202610 min read
Chapter 03 · Positional Bias

Does the order of results matter?

Testing positional bias: whether AI models favor the first hotel they see — and how much of the effect is real vs. API noise.

Mar 3, 20267 min read
Chapter 02 · Brand Bias

AI recommends branded hotels 60% of the time

A 20-point lift from the brand name alone. We hid brand names in a paired control — the bias collapsed. Here’s what it means for independents.

Feb 22, 20269 min read
Chapter 01 · Feature Selection

What AI actually weighs when picking a hotel

Location, price, reviews, amenities — ranked by how much each one moves the AI’s choice. Hint: it’s not what you’d guess.

Feb 14, 20268 min read
Get new studies first

Subscribe to Huxo Research

One study a month. No marketing fluff — just the data, the method, and the playbook for independent hotels.

FreeUnsubscribe anytimeNo spam