Booking.com utilizes various machine learning platforms to influence billions of travel decisions. These platforms operate behind the scenes, supporting the company's core services.
The company's AI evolution is structured into three layers: data management, ML engineering, and domain intelligence. The data management layer addresses database evolution, scale challenges, and cloud migration. The ML engineering layer focuses on model serving at scale and feature engineering. The domain intelligence layer provides an overview of machine learning platforms, with a deep dive into one specific platform's development.
Booking.com began running its first A/B experiment in 2005, nine years after its founding. Today, all changes, from CSS adjustments to infrastructure updates, undergo experimentation. At any given time, a user visiting Booking.com may be subjected to over 1,000 active experiments. The company has conducted more than 150,000 experiments to date.
The success rate for Booking.com's experiments is less than 25%. This low success rate is viewed not as a failure, but as an opportunity for rapid learning. This approach has fostered a data-driven culture, eliminating internal debates by relying on test results and promoting a culture of humility where no single expert's opinion overrides empirical data.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's briefNew every morning, and the back catalogue is archived by date.
Booking.com presented on the evolution of its AI platforms, detailing its journey from 2005 to the present. The presentation covered the development of its data management, ML engineering, and domain intelligence layers, highlighting the company's extensive use of A/B experimentation.