Booking.com and OpenAI personalize travel at scale
By integrating its data systems with OpenAI’s LLMs, Booking.com delivers smarter search, faster support, and intent-driven travel experiences.
As one of the world’s largest travel marketplaces, Booking.com makes it easier for millions of travelers to experience the world, offering seamless access to flights, stays, and activities in one place.
With OpenAI, the company saw an opportunity to become a true travel companion, addressing the discovery phase to help travelers uncover destinations and experiences they didn’t even know they wanted.
“When ChatGPT launched in 2022, I got this tingle,” says Adrienne Enggist, Senior Director of Product Marketplace at Booking.com. “It reminded me of the early days of broadband access—this massive opportunity to change how people engage with travel. We knew this could help us finally crack the discovery challenge.”
To date, Booking.com has launched multiple AI-powered solutions with OpenAI to make travel planning easier and more intuitive.
Booking.com had been using machine learning for over a decade, but traditional models and rule-based systems struggled to capture the nuances of user intent - especially in the early discovery phase.
“You might want to go on a romantic getaway, but make it cheesy,” says Rob Francis, Booking.com’s CTO. “There’s no filter for heart-shaped beds or Elvis impersonators. Traditional search just wasn’t built to unlock that kind of intent.”
Although the platform offered hundreds of filters, they were only helpful if travelers knew exactly what to look for. The rise of large language models presented a new opportunity to move to a more conversational, discovery-driven experience.
“We’ve always been really good at the last mile - getting people from search to booking,” says Enggist. “But discovery was different. We needed a way to meet customers earlier in the process, when they were still figuring out what they wanted.”
Booking.com quickly assembled a task force to bring the AI Trip Planner to life:
- Leveraging existing ML infrastructure: The team integrated OpenAI’s GPT models with Booking.com’s proprietary data on properties, pricing, and availability.
- Rapid development cycle: The first prototype, capable of destination discovery and itinerary building, was launched in just 10 weeks.
- Focus on natural language: The model was trained to understand conversational prompts and map them to structured data like dates, locations, and property availability.
The AI Trip Planner allowed users to ask open-ended questions like, “Where should I go for a romantic weekend in Europe?” It could generate destination suggestions, build itineraries, and pull in real-time availability and pricing data from Booking.com’s database.
One of the key breakthroughs was combining structured and unstructured data. “We’d spent years fine-tuning our structured data, like pricing, availability, cancellation policies,” says Enggist. “But now we could layer in unstructured data, like user reviews, natural language descriptions, and generate curated suggestions based on both.”
Another hallmark was the speed with which the Booking.com team was able to move. “The collaboration has been amazing,” says Joe Futty, VP Product Marketplace at Booking.com. “We started with OpenAI’s API, ran a hackathon, and within 10 weeks, we launched the AI Trip Planner. That’s the power of working with a team who’s not just providing technology but working alongside us to figure out what’s possible.”
The AI Trip Planner has since expanded to handle more complex requests and deeper personalization. “When you look at Booking.com data about how people have booked travel over the last 20 years, the top 15 destinations in Europe are heavily over-touristed,” notes Enggist. “AI can also help surface the hundreds of other destinations which are not that far away and have equally fantastic experiences, are not over-touristed, and are full of even new opportunities to be discovered.”
The success of the AI Trip Planner laid the foundation for more AI-driven products. Today, Booking.com has launched additional flagship capabilities with OpenAI’s models:
Solution | Challenge it solves | How it works |
Smart Filters | Traditional search relied on drop-down menus and checkboxes, limiting travelers to a small number of filters. | Uses GPT‑4o mini to understand natural language prompts like “sunset views” or “great gym”. |
Property Q&A | Many travelers have specific questions about properties that aren’t easily answered in a static listing. | OpenAI’s LLMs were fine-tuned on Booking.com’s user-generated content and property descriptions. |
AI Review Summaries | Travelers often struggle to sort through thousands of reviews when comparing properties. | GPT‑4o mini analyzes and summarizes reviews into key themes (e.g. cleanliness, location, amenities). |
Help Me Reply | Manages guest communications efficiently and improves response times. | Built using OpenAI’s models to generate automated responses and customizable message templates. |
Booking.com has also built a stronger foundation for future AI development. OpenAI’s models were integrated through Booking.com’s existing APIs and data infrastructure, allowing teams to rapidly test and iterate on new features.
While Booking.com is still collecting long-term performance data, they have already seen measurable lift in engagement and satisfaction:
- Increased engagement: AI Trip Planner has kept users on the platform longer as they explore personalized itineraries.
- Faster search: Smart Filters have made it easier for travelers to find specific results, reducing the time spent on search.
- Fewer customer support contacts: Property Q&A has lowered support volumes with more accurate in-app answers.
- Higher booking confidence: Review summarization has helped travelers make faster decisions with less uncertainty.
“One of the biggest insights was how quickly customer behavior changed,” says Enggist. “At first, people were just typing ‘Myrtle Beach,’ basically using it like a search engine. But now we’re seeing more detailed, conversational queries: ‘I want to go to a quiet beach in September with my dog.’”
“OpenAI’s models are the most capable at understanding intent and adapting to real-world complexities,” Francis says. “We’ve been working with machine learning for over a decade, but OpenAI helped us close the gap between understanding intent and fulfilling it.”
What sets OpenAI apart, according to Booking.com’s leadership, isn’t just the technology - it’s the collaborative approach.
“The co-creation of the future is a hallmark of working with OpenAI,” says Enggist. “We can bring them open questions or early-stage ideas, and they help us shape what’s possible.”
Francis echoes this sentiment: “Working with OpenAI isn’t just about doing what’s in front of us - it’s about asking, ‘What’s next?’”
Booking.com sees an opportunity to create an even more immersive, agent-driven experience. “We want to build a concierge-like companion that follows you through the entire travel journey,” says Enggist. “Not just helping you book the trip; rebooking your flight if it’s canceled, finding a new hotel if you’re delayed, and suggesting restaurants nearby when you arrive.”
“AI is becoming the operating fabric at Booking.com, and OpenAI’s models have unlocked a new level of understanding and personalization. This isn’t just about search. It’s about creating a richer, more connected travel experience.”
