← Airbnb Interview Insights

Airbnb·Data Scientist·Technical Phone Screen·Senior

Senior
Jul 2026

Summary

Airbnb data science interview with a pretty gnarly causal inference scenario. No fluff, just one meaty question about estimating impact when you've already blown past the experiment window.

Questions Asked (1)

Q1

A feature was launched to 100% of users with no control group. How would you estimate the causal impact of that launch, what data would you need, what assumptions are you making, and how do you communicate the uncertainty?

A/B Testing & ExperimentationProduct Analytics & MetricsAdaptability & Ambiguity
Author's notes

This one stung a little because I started with pre-post analysis and the interviewer just waited.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Acknowledge the limitation of no control group and propose quasi-experimental methods like difference-in-differences, synthetic control, or interrupted time series. Outline the data needed (pre/post metrics, covariates, potential control groups) and the assumptions (parallel trends, no concurrent shocks). Communicate uncertainty via confidence intervals and sensitivity analyses.

Pro tip: Emphasize that the best approach depends on the specific context—e.g., whether a natural control group exists (like a holdout in another region) or if you can use pre-launch trends. Always discuss the trade-offs between different methods and the importance of validating assumptions.

1. Clarify the goal and constraints

Understand what decision the causal estimate will inform and what data is available. Identify if any natural control groups exist (e.g., users who couldn't access the feature due to technical issues, or similar markets).

2. Choose a quasi-experimental method

Select an appropriate method based on data availability: difference-in-differences (if a control group exists), synthetic control (if multiple pre-periods and a donor pool), interrupted time series (if only one unit), or propensity score matching (if covariates available).

3. Identify required data and assumptions

List data needed: pre- and post-launch metrics for treated and control units, covariates for matching, and time series data. State key assumptions: parallel trends, no spillover, no concurrent events, and correct model specification.

4. Estimate and validate

Apply the method, check assumptions (e.g., pre-trends for DiD), and run sensitivity analyses (e.g., placebo tests, varying control groups). Quantify uncertainty with confidence intervals or Bayesian credible intervals.

5. Communicate uncertainty and limitations

Present the estimate with uncertainty ranges, explain assumptions and their plausibility, and discuss how violations would affect conclusions. Recommend follow-up experiments if possible.

Key Points to Mention

  • Difference-in-differences and its parallel trends assumption
  • Synthetic control method for constructing a counterfactual
  • Interrupted time series analysis for single-unit interventions
  • Propensity score matching to create comparable groups
  • Sensitivity analysis and placebo tests to assess robustness
  • Confidence intervals and Bayesian methods for uncertainty quantification

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