Expedia Data Scientist interview questions

4 Data Scientists have shared notes from their Expedia interviews, with the questions they were asked in each round. That is 11% of the 36 Expedia interview notes on Screna AI.

4 Data Scientist interview notes

Expedia·Data Scientist·Onsite - Cross-functional / Panel

Jul 2026
Expedia data scientist panel, and the whole thing was basically a stress test disguised as a case study. Three stakeholders with three different KPIs and 48 hours to prep something they said would take 'a few hours.' The depth they expected did not match that framing at all.
  • Stakeholders from different teams each want a different primary KPI for the same product decision. How do you get alignment before you've even started the analysis?
  • During a panel interview, a question runs long and gets confusing. What do you do in the moment?
  • Walk us through how you'd structure a data-driven recommendation that has real trade-offs and risks. What narrative framework do you use?
  • After your presentation, two panelists give you directly conflicting feedback. How do you respond without getting defensive or just agreeing with whoever spoke last?
  • How would you push back on interview constraints like timeline expectations, relocation requirements, or compensation, without damaging the relationship?

“This one tripped me up because I jumped straight into talking about metrics frameworks before addressing the actual political problem.”

View Post

Expedia·Data Scientist·Technical Phone Screen

May 2026
Deep technical interview for a Data Scientist role at Expedia focused entirely on ML evaluation and deployment for a hotel ranking model. One long multi-part question that covers basically everything from offline metrics to production monitoring. Felt more like a system design session than a typical DS interview.
  • How would you design an offline evaluation plan for a hotel ranking model that avoids data leakage, accounts for position bias, and validates that conversion probability predictions are well-calibrated?
  • Which ranking metrics would you report for this model, and can you explain the formulas and why they reflect actual business value rather than just model performance?
  • How would you identify the key drivers of model predictions without leaking target information into your feature analysis?
  • Walk through how you'd roll out this ranking model safely, including shadow mode, canary deployments, guardrail alarms, drift detection, and an automatic rollback policy.
  • How would you verify that improving a surrogate objective offline actually translates to gains on the real business KPI, and what would you do if the offline-to-online relationship breaks down?

“This is where I spent the most time.”

View Post

Expedia·Data Scientist·Technical Phone Screen

May 2026
Technical screen for a DS role at Expedia that went deep into data quality and pipeline validation for hotel search data. The question was essentially one long case study, and it covered a lot of ground fast.
  • You've inherited an unfamiliar hotel search dataset with almost no documentation. Walk through how you'd systematically explore the schema, verify keys, and understand what tables actually represent.
  • How would you profile distributions, missingness, and issues around timezones, locale, and currency across a travel dataset?
  • How do you detect duplicate records and join inflation when linking searches, impressions, clicks, bookings, and cancellations?
  • How would you validate that events follow the correct sequence (search to impression to click to booking to cancellation), and how do you handle late-arriving data?
  • Walk through how you'd correctly compute metrics like bookings per search within a 7-day window, margin as price minus cost, and the difference between GMV and contribution margin.
  • How would you write data quality tests and data contracts covering nullability, uniqueness, referential integrity, and numeric range checks for this kind of pipeline?
  • What are specific pitfalls in travel data around multi-room bookings, partial cancellations, rebookings, cross-currency FX timing, and adult vs. child guest counts, and how would you detect each?

“Started with information_schema and just ran describe on everything, which felt obvious but they seemed fine with it.”

View Post

Expedia·Data Scientist·Technical Phone Screen

Apr 2026
Expedia DS interview for their Search team, focused entirely on a hotel-ranking model case. The whole thing was one long multi-part question that spiraled through KPIs, experimentation, attribution, and profit estimation. Pretty intense, no fluff.
  • Define a single primary KPI for a hotel-ranking model serving enterprise clients who care about profitable bookings, and list at least three guardrail metrics with specific thresholds.
  • How would you validate that offline proxy metrics like margin-weighted NDCG correlate with your online KPI? Describe the analysis design, acceptable correlation ranges, and what you'd do if they're misaligned.
  • Design an A/B test for this ranking model: randomization unit, traffic split, ramp strategy, MDE and sample size calculation, pre-experiment checks, and variance reduction techniques.
  • How would you detect and prevent metric gaming and novelty effects in this ranking experiment, and what would your rollback criterion be?
  • Bookings are flat but cancellations rise 15% in the treatment group. Do you ship or rollback? Justify using expected profit impact and confidence intervals.
  • Estimate the incremental gross profit per search with a 95% confidence interval, and explain how you'd separate true incrementality from attribution.
  • For paid channels, propose a multi-touch attribution approach and explain how you'd calibrate it against holdout or geo-based tests.

“I went with something like margin-adjusted bookings per search over a 7-day window, which felt right for the client value angle.”

View Post