← Airbnb Interview Insights

Airbnb·Data Scientist·Technical Phone Screen·Senior

Senior
May 2026

Summary

Airbnb data science interview with a single very deep experimentation question. The whole thing was basically a case study on designing an A/B test for a new Wi-Fi badge feature, and it went several layers deeper than I expected.

Questions Asked (1)

Q1

You work on a two-sided travel search marketplace. Product wants to add a 'High Wi-Fi' badge and filter to help remote workers find listings. Design an experiment to decide whether to launch it, covering randomization strategy, metrics, power analysis, analysis plan, and a dollar-value decision rule.

A/B Testing & ExperimentationProduct Analytics & MetricsPricing & Monetization
Author's notes

This was a monster.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by clarifying the product change and defining success metrics for both sides of the marketplace. Then outline a randomized experiment design with proper power analysis, and finish with a decision rule that translates metric lifts into dollar value.

Pro tip: Emphasize that in a two-sided marketplace, you must consider spillover effects and network effects; randomize at the guest level but analyze at the listing level to avoid contamination.

1. Define Hypothesis and Metrics

State the hypothesis that the High Wi-Fi badge/filter improves booking conversion for remote workers. Define primary metric (e.g., booking conversion rate for remote-worker segment) and guardrail metrics (e.g., overall conversion, host satisfaction).

2. Randomization Strategy

Randomize at the guest level to avoid spillover, but ensure listings are not double-counted by using a cluster randomized design if needed. Consider stratifying by guest type (remote worker vs. leisure) and listing characteristics.

3. Power Analysis and Sample Size

Calculate required sample size based on minimum detectable effect (MDE) for the primary metric, using historical variance and desired power (80%) and significance level (5%). Account for two-sided marketplace by powering for both guest and host outcomes.

4. Analysis Plan

Pre-register analysis: use intent-to-treat, compare primary metric via t-test or regression with covariates. Check for novelty effects, segment by remote-worker status, and monitor guardrail metrics for degradation.

5. Dollar-Value Decision Rule

Estimate incremental revenue from lift in bookings, subtract implementation and maintenance costs, and compute net present value. Launch if NPV > 0 and guardrails are not violated, with a threshold (e.g., ROI > 20%).

Key Points to Mention

  • Two-sided marketplace considerations: network effects, spillover, and randomization unit
  • Primary metric: booking conversion rate for remote workers; guardrails: overall conversion, host acceptance rate
  • Power analysis: MDE, sample size, and duration; account for seasonality
  • Analysis: intent-to-treat, segment analysis, novelty effect check
  • Dollar-value: incremental revenue, costs, NPV, and decision threshold
  • Potential biases: selection bias, measurement error in Wi-Fi quality

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.