← Yelp Interview Insights

Yelp·Data Scientist·Technical Phone Screen·Senior

Senior
Apr 2026

Summary

Yelp data science interview with a meaty A/B testing case built around redesigning a disliked social app feature. The whole question was basically one long multi-part problem that kept going deeper the more you answered.

Questions Asked (5)

Q1

Pick a consumer app feature you dislike and define a single or composite metric to measure how users respond to a proposed change.

Product Analytics & MetricsA/B Testing & ExperimentationProduct Sense & Ideation
Author's notes

I went with Instagram's suggested posts in the home feed, which felt like a safe pick.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Choose a well-known consumer app feature that you genuinely dislike, then propose a specific change and define a metric (single or composite) to measure user response. Structure your answer by first describing the feature and your proposed change, then explaining how you would measure success using a metric that captures the desired user behavior. Emphasize the rationale behind your metric choice and how it aligns with business goals.

Pro tip: When defining a composite metric, explain how you would weight its components and validate that it's not gameable. Also, mention how you would set up an A/B test to measure the metric's change, showing end-to-end thinking.

1. Select a feature and articulate the problem

Pick a consumer app feature you dislike and clearly explain why it's problematic from a user or business perspective. This sets the stage for your proposed change.

2. Propose a specific change

Describe a concrete modification to the feature that addresses the problem. Be clear about what the change entails and its intended impact on user behavior.

3. Define the metric

Choose a single or composite metric that directly measures user response to the change. Explain what the metric captures and why it's appropriate.

4. Justify the metric and outline measurement

Explain how the metric aligns with business goals, how you would track it (e.g., via A/B test), and any potential pitfalls or guardrail metrics to consider.

Key Points to Mention

  • Clear definition of the feature and the problem it causes
  • Specific and actionable proposed change
  • Metric selection rationale (e.g., engagement, retention, satisfaction)
  • Composite metric construction (if used) with weighting and validation
  • A/B testing methodology to measure the metric
  • Guardrail metrics to ensure no negative side effects

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

Q2

How would you estimate the required sample size for the A/B test, and how long should the experiment run? Walk through your assumptions and calculations.

A/B Testing & ExperimentationProduct Analytics & Metrics
Author's notes

This is where I got a bit tangled.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by clarifying the metric and test design, then use a power analysis formula to compute the required sample size per variant based on baseline rate, minimum detectable effect, significance level, and power. Finally, translate sample size into duration using daily traffic and consider practical constraints like novelty effects and business cycles.

Pro tip: Always discuss the trade-off between MDE and duration: smaller MDEs require exponentially more samples, so align with stakeholders on the smallest effect that justifies the test. Also, mention that you'd validate assumptions with a pilot or historical data to avoid underpowered tests.

1. Define the metric and test parameters

Identify the primary metric (e.g., conversion rate, click-through rate) and specify the baseline value, significance level (α), power (1-β), and the minimum detectable effect (MDE) you care about.

2. Calculate sample size per variant

Use the standard formula for two-proportion z-test: n = (Zα/2 + Zβ)^2 * (p1(1-p1) + p2(1-p2)) / (p2 - p1)^2, where p1 is baseline and p2 = p1 + MDE. For continuous metrics, use the t-test formula with variance.

3. Determine total sample and duration

Multiply per-variant sample by number of variants (usually 2) to get total sample. Divide by daily traffic eligible for the test to estimate days needed, then round up to full weeks to account for weekly seasonality.

4. Adjust for practical considerations

Account for novelty effects, ramp-up periods, and potential data loss (e.g., bot filtering). Consider running at least one full business cycle (e.g., 1-2 weeks) even if sample size is reached sooner.

5. Validate and communicate assumptions

Sanity-check with historical data or a pilot, and clearly communicate the assumptions and trade-offs (e.g., longer duration vs. smaller MDE) to stakeholders.

Key Points to Mention

  • Baseline conversion rate and its impact on required sample size (variance is highest at p=0.5).
  • Minimum detectable effect (MDE) and its inverse square relationship with sample size.
  • Statistical power (typically 80%) and significance level (typically 5%).
  • Daily traffic and the need to run for full weeks to capture weekly seasonality.
  • Potential pitfalls: novelty effects, multiple testing, and peeking (early stopping).
  • Alternative approaches: sequential testing or Bayesian methods if frequentist assumptions are problematic.

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

Q3

Which user segment or geography would you target first for this test, and what's your reasoning?

A/B Testing & ExperimentationProduct Strategy
Author's notes

Said English-speaking markets with high DAU and relatively homogeneous usage patterns, basically to reduce variance.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by clarifying the test's goal and success metrics, then propose a specific user segment or geography based on data-driven factors like traffic volume, conversion rates, and strategic importance. Justify your choice by explaining how it balances statistical power, business impact, and risk, and mention how you'd validate and potentially expand the test later.

Pro tip: Show that you think about both statistical validity and business practicality: choose a segment with enough volume to detect meaningful effects, but also consider if the results will generalize to other segments. Mention that you'd run a power analysis to confirm sample size before committing.

1. Clarify test objective and metrics

Ask or state the primary goal of the test (e.g., increase reviews, clicks, bookings) and the key success metric. This ensures your targeting aligns with what you're trying to learn or optimize.

2. Evaluate potential segments/geographies

List candidate segments (e.g., new vs. returning users, mobile vs. desktop, specific cities) and geographies (e.g., high-traffic cities, underperforming markets). Consider factors like traffic volume, baseline conversion, and strategic value.

3. Assess statistical power and feasibility

Estimate whether the segment has enough users to detect a meaningful effect size. Consider running a power analysis or using historical data to check variance and expected lift.

4. Consider business impact and risk

Weigh the potential upside (e.g., revenue, engagement) against risks (e.g., user experience, cannibalization). Choose a segment where a positive result would be impactful and a negative result wouldn't be catastrophic.

5. Propose a phased approach

Recommend starting with a small, representative segment (e.g., one city or user type) to validate the test, then expanding if results are promising. Mention how you'd monitor and decide to scale.

Key Points to Mention

  • Statistical power and sample size: ensure the segment has enough users to detect a meaningful effect.
  • Business impact: target a segment where the test outcome could drive significant value (e.g., high-revenue city or high-growth user group).
  • Representativeness: consider whether results will generalize to the broader user base; avoid overly niche segments unless justified.
  • Risk mitigation: start with a low-risk segment to avoid negative user experiences at scale.
  • Data-driven selection: use historical data (e.g., traffic, conversion rates, engagement) to inform the choice.
  • Scalability: plan how to expand the test if successful, and what metrics would trigger a rollout.

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

Q4

What statistical test would you use to compare the control and treatment groups, and why is it the right choice here?

A/B Testing & ExperimentationProduct Analytics & Metrics
Author's notes

Went with a two-sample t-test for the continuous engagement metric, mentioned checking normality assumptions and that with large enough n the CLT covers it anyway.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by clarifying the metric type (e.g., conversion rate, revenue per user) and the experimental design (sample size, randomization). Then recommend a test based on assumptions: for continuous metrics use Welch's t-test if normality holds, otherwise Mann-Whitney U; for binary metrics use a two-proportion z-test or chi-square. Justify by linking to statistical power, robustness to violations, and business impact.

Pro tip: Mention that at Yelp, where metrics like click-through rates and session durations are common, you'd also consider sequential testing or bootstrapping to handle non-normal data and peeking, showing you understand practical experimentation at scale.

1. Identify the metric type

Determine whether the metric is continuous (e.g., revenue, time on page) or binary (e.g., conversion, click). This dictates the family of tests.

2. Check assumptions

Assess normality, variance homogeneity, and sample size. For large samples, t-tests are robust; for small or skewed data, consider non-parametric alternatives.

3. Select the appropriate test

For continuous metrics: Welch's t-test (unequal variances) or Mann-Whitney U. For binary metrics: two-proportion z-test or chi-square test.

4. Justify the choice

Explain why the test is suitable: e.g., Welch's t-test controls Type I error under unequal variances; non-parametric tests don't assume normality.

5. Consider practical extensions

Mention adjustments for multiple testing, sequential analysis, or bootstrapping for complex metrics like ratios or percentiles.

Key Points to Mention

  • Metric type (continuous vs. binary) drives test selection
  • Assumptions: normality, equal variance, independence
  • Welch's t-test for continuous metrics with unequal variances
  • Two-proportion z-test or chi-square for binary metrics
  • Non-parametric alternatives (Mann-Whitney U) for non-normal data
  • Practical considerations: sample size, multiple comparisons, sequential testing

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

Q5

The overall test result is not statistically significant, but the treatment group shows higher engagement. How do you interpret this, and do you (a) fully launch, (b) rerun or extend the test, or (c) dig into a specific subgroup like younger users?

A/B Testing & ExperimentationAdaptability & AmbiguityRoot Cause Analysis
Author's notes

This was the most interesting part of the question.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by acknowledging that a non-significant overall result means we cannot confidently attribute the engagement lift to the treatment, so launching fully is premature. Then propose a structured path: validate the test's power and data quality, explore pre-registered subgroups with caution, and decide whether to extend, iterate, or dig deeper based on the business context and risk.

Pro tip: Emphasize that subgroup analysis should be pre-registered or treated as hypothesis-generating, not confirmatory—otherwise you risk p-hacking and false positives. Also, consider the cost of a false launch versus the cost of delaying, and align with stakeholders on the decision threshold.

1. Assess test validity and power

Check if the test was adequately powered, if there were any data quality issues, and whether the non-significance is due to low sample size or high variance. Calculate the minimum detectable effect and confidence intervals to understand the uncertainty.

2. Interpret the overall result

A non-significant overall result means we cannot reject the null hypothesis; the observed engagement lift could be due to chance. Avoid over-interpreting the direction of the effect without statistical significance.

3. Evaluate subgroup analysis

If subgroups were pre-registered, examine them with appropriate corrections for multiple comparisons. If not, treat any findings as exploratory and require validation in a follow-up test.

4. Consider business context and risk

Weigh the potential upside of the engagement lift against the risk of a false positive. Consider the cost of launching, the reversibility, and whether the engagement metric aligns with key business goals.

5. Recommend next steps

Based on the above, recommend either extending the test to increase power, running a new test focused on a promising subgroup, or not launching. Avoid fully launching without stronger evidence.

Key Points to Mention

  • Statistical significance vs. practical significance: a non-significant result doesn't mean no effect, but we can't be confident.
  • Power analysis and sample size: the test may have been underpowered to detect the observed effect.
  • Confidence intervals: they provide a range of plausible effect sizes and help assess uncertainty.
  • Multiple comparisons problem: subgroup analyses increase the chance of false positives.
  • Pre-registration of subgroups: if not pre-registered, subgroup findings are hypothesis-generating only.
  • Business impact and decision-making: consider the cost of false positives vs. false negatives, and align with stakeholders.

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