NOV 4, 2026

When history fails you, borrow from geography

How Airbnb used sequential geographic recovery signals and prior propagation to generate reliable corridor-level forecasts when local data was scarce.By:...

Data Pipeline API Design Data Forecasting

Read full article →

Share Share

CASTLE: training natural language search before the first real query

How we addressed the cold-start problem for Airbnb’s natural language search by jointly generating synthetic training data — queries and relevance labels —...

FrontendData Science

7 min

Airbnb28d ago

Beyond synthetic testing: Capturing and replaying real database workloads at Airbnb

How we capture real production database traffic at Airbnb and replay it offline to load-test, plan capacity, and de-risk upgrades.By: Zuofei Wang, Erluo...

FrontendData Science

11 min

Weekly Brief

Top 10 engineering articles delivered every Monday.

AirbnbSep 29, 2026

Personalization without user identity

How Airbnb uses proximity signals to personalize without relying on individual user history.By: Wei Jiang, Bin Xu, Bharathi Thangamani, Weiwei Guo, Sundar...

FrontendData Science

8 min