Data Scientist interview
at Airbnb.

Tell-me-about-a-time stories on ownership, conflict, and impact — scored against this company's real values.

1. 01 Airbnb's mission is to create a world where anyone can belong anywhere; tell us about a project where you used data to help an underserved group of users feel more included.
2. 02 Describe a time you 'were a good host' to a stakeholder by going out of your way to make a non-technical partner feel supported and understood during an analysis.
3. 03 Tell us about a time you embraced the adventure and championed a risky, unproven analytical bet that others doubted, and what you learned from the result.
4. 04 Walk us through a moment when your data analysis contradicted a leader's strongly held intuition, and how you navigated that disagreement while staying caring and direct.

The hard screen for the craft itself — talked through out loud, not whiteboarded in your head.

1. 01 Given Airbnb's bookings and listings tables, write a SQL query to compute the search-to-book conversion funnel by city and month.
2. 02 How would you design and power an A/B test for a new guest search-ranking change, including choosing the primary metric, computing sample size, and guarding against peeking?
3. 03 A host-side feature improved host earnings but appeared to lower guest booking conversion; how would you statistically untangle whether this is a real two-sided marketplace tradeoff or noise?
4. 04 Explain how you would detect and correct for interference (network effects) when running an experiment on a two-sided marketplace where treating hosts can affect control guests.

Open-ended design of the systems this company actually runs, with the interviewer probing your tradeoffs.

1. 01 Design the experimentation platform that lets Airbnb teams run thousands of concurrent A/B tests across guests and hosts without cross-contamination.
2. 02 Design the metrics and logging pipeline that powers Airbnb's search-to-book funnel dashboards across listings, regions, and devices.
3. 03 Design a measurement framework to quantify the long-term impact of changing Airbnb's listing search ranking on host retention and listing diversity.
4. 04 Design an anomaly-detection system that flags sudden drops in booking conversion or spikes in cancellations across markets in near real time.