AI BriefingPersonalizing Large-Scale Travel Experiences with OpenAI
Key point
Booking.com built an AI solution using OpenAI's LLM to understand users' complex intent and deliver personalized travel experiences.
Details
Booking.com noted that existing rule-based systems and filtering methods have limitations in capturing users' subtle intent (e.g., a 'romantic atmosphere'). To address this, it integrated OpenAI's LLM with its own data systems, beginning to offer personalized experiences that support the travel journey from the 'Discovery' stage onward, beyond simple search.
The AI Trip Planner had a prototype developed in just 10 weeks, combining the GPT model with Booking.com's data on accommodations, pricing, and availability. In particular, by leveraging both Structured data such as prices and policies and Unstructured data such as user reviews and property descriptions together, more sophisticated suggestions become possible.
Booking.com currently operates the following key AI solutions:
- AI Trip Planner: Provides destination recommendations, itinerary generation, and real-time booking information through natural language questions.
- Smart Filters: Uses GPT-4o mini to understand natural language requests like 'sunset view' or 'good gym', analyzing reviews and images to show relevant results.
- Property Q&A: An LLM answers specific questions about a property, enhancing user convenience.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.