AI experimentation infrastructure at travel-industry scale.
Experimentation and attribution infrastructure for a top-three OTA — running tens of thousands of concurrent experiments across paid channels and product surfaces.
Client
Booking.com
Sector
Travel & eCommerce
Duration
22 months
Team
14 (senior product engineers, data engineers, ML infra specialists, an SRE embed)
Where Booking.com was when we started.
Booking.com operates one of the world's largest continuous experimentation programmes. Every product surface, ranking model, and paid-channel touchpoint is under experiment simultaneously, and the marginal cost of a bad decision — measured in bookings — is nine figures a year. As the company's AI investment scaled, the experimentation platform started to need capabilities the original architecture wasn't built for.
The problem, unvarnished.
- Attribution across paid, organic, and product touchpoints — with cookie deprecation making the traditional multi-touch model unreliable
- Experiment concurrency at a scale where naive analysis leaks between variants
- Model-serving latency budgets under 40ms at global peak, across dozens of ranking and recommendation models
- A growing gap between experiment-platform capability and what data scientists were being asked to test
How we scoped and sequenced the work.
01
Causal attribution on first-party signal
We rebuilt attribution around causal inference on first-party touchpoints, augmented with channel-level media mix modelling. Weekly refresh; monthly backtest against holdout markets; a shared read that the finance team accepts.
02
Experiment concurrency and interaction control
Concurrency-safe experiment design with interaction detection — the platform now surfaces variant interactions to the data science team before results are read, not after a bad decision is shipped.
03
Low-latency model serving at global scale
Rebuilt the model-serving path with edge caching, model quantisation, and traffic-shaping to hold 40ms latency budgets across every region. Model rollouts moved from weekly to continuous.
04
Platform-team enablement, not model-team ownership
We stayed embedded until Booking's platform team could operate, evaluate, and extend the system without us in the loop.
What we shipped.
An upgraded experimentation, attribution, and model-serving platform underneath Booking.com's product and marketing surfaces. Concurrency-safe experiments, causal attribution grounded in first-party data, and model-serving that meets global latency budgets.
The numbers that matter.
2.4x
Improvement in blended paid ROAS
After reallocation informed by the new causal attribution model, measured over two quarters against the pre-change baseline.
40ms
P99 model-serving latency, global
Held across all regions during peak booking-season traffic, on a model surface that previously breached budget on weekly basis.
10,000+
Concurrent experiments
With interaction detection surfaced to the data science team automatically — up from a low-thousands ceiling on the prior platform.
What we built it on.
Bring us your travel & ecommerce brief.
Book a 30-minute discovery call. A senior practitioner from the same practice that shipped this engagement will scope yours.
or email contact@headify.com