← Stripe Interview Insights

Stripe·Data Scientist·Technical Phone Screen·Senior

SeniorPrefer not to say
May 2026Remote

Summary

Stripe DS interview that was basically a full experiment design gauntlet compressed into one session. Heavy on stats and causal inference, less on product intuition. Left feeling like I'd passed a grad school qualifying exam.

Questions Asked (5)

Q1

You're launching an email targeting model where users above a score threshold get the email and others don't. What's your primary success metric and which two guardrail metrics would you use, and why?

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

I went with 7-day purchase rate as primary, which felt obvious.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by clarifying the business objective (e.g., increase engagement or revenue) and then define a primary success metric that directly measures that objective, such as incremental revenue per user or conversion rate. Next, select two guardrail metrics that ensure the model doesn't harm user experience or long-term health, like unsubscribe rate and email complaint rate. Explain how you would measure these metrics in an A/B test comparing the targeted model against a control (e.g., no email or random targeting).

Pro tip: Emphasize that guardrail metrics should be chosen to detect unintended consequences of targeting, such as alienating users who receive irrelevant emails, and mention that you'd monitor them for statistical significance and practical significance.

1. Clarify the business goal

Ask or state the primary objective of the email campaign (e.g., drive purchases, increase engagement) to ensure the success metric aligns with business value.

2. Define the primary success metric

Choose a metric that directly measures the campaign's impact on the goal, such as incremental revenue per user or conversion rate, and explain how it will be measured in an experiment.

3. Select guardrail metrics

Pick two metrics that capture potential negative side effects, such as unsubscribe rate (user annoyance) and email complaint rate (reputation damage), and justify why they are critical.

4. Design the experiment

Outline an A/B test where the treatment is the targeted email model and the control is either no email or a random/untargeted email, to isolate the model's incremental effect.

5. Monitor and iterate

Explain how you would monitor both primary and guardrail metrics for statistical significance and practical significance, and decide whether to launch, iterate, or stop.

Key Points to Mention

  • Incremental lift measurement (e.g., comparing targeted vs. holdout group) to avoid selection bias
  • Unsubscribe rate as a guardrail to prevent user annoyance and list fatigue
  • Email complaint rate (or spam report rate) as a guardrail to protect sender reputation
  • Statistical power and sample size considerations for detecting changes in guardrail metrics
  • Long-term vs. short-term trade-offs (e.g., revenue now vs. user trust later)
  • Segment-level analysis to ensure the model doesn't disproportionately harm certain user groups

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

Q2

With a baseline 7-day purchase rate of 5% and an expected relative lift of 8%, calculate the minimum per-arm sample size for a two-sided test at alpha=0.05 and 80% power. Show your work.

A/B Testing & Experimentation
Author's notes

This is where I got sweaty.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

First, convert the relative lift into an absolute difference by multiplying the baseline rate by the lift (5% * 8% = 0.4 percentage points). Then, apply the standard sample size formula for comparing two proportions: n = (Z_α/2 + Z_β)^2 * (p1(1-p1) + p2(1-p2)) / (p2 - p1)^2, using Z_α/2 = 1.96 and Z_β = 0.84. Finally, compute the result and round up to the nearest whole number.

Pro tip: Always clarify whether the sample size is per arm or total, and mention that this calculation assumes no peeking and a fixed horizon; in practice, you might adjust for sequential testing or use simulation for more complex designs.

1. Define parameters

Identify baseline conversion rate (p1 = 0.05), relative lift (8%), and compute absolute lift (Δ = 0.004) and treatment rate (p2 = 0.054). Also note alpha (0.05, two-sided) and power (80%).

2. Determine critical values

For a two-sided test at alpha=0.05, Z_α/2 = 1.96. For 80% power, Z_β = 0.84 (since β=0.20).

3. Apply sample size formula

Use the formula for two proportions: n = (Z_α/2 + Z_β)^2 * (p1(1-p1) + p2(1-p2)) / (p2 - p1)^2. Plug in the values: (1.96+0.84)^2 = 7.84; p1(1-p1)=0.0475; p2(1-p2)=0.051084; sum=0.098584; Δ^2=0.000016; n = 7.84 * 0.098584 / 0.000016 ≈ 48,306 per arm.

4. Round and interpret

Round up to the next whole number (48,307) and state that this is the minimum per-arm sample size. Optionally, discuss practical considerations like traffic and duration.

Key Points to Mention

  • Conversion of relative lift to absolute difference
  • Use of Z-scores for alpha and power (1.96 and 0.84)
  • Sample size formula for two independent proportions
  • Assumption of equal variance or use of pooled variance (though formula uses unpooled)
  • Rounding up to ensure sufficient power
  • Clarification that sample size is per arm

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

Q3

Describe a ramp plan with sequential monitoring that keeps type-I error controlled. What interim looks would you schedule and what are your stopping rules?

A/B Testing & ExperimentationTechnical Trade-offs
Author's notes

Talked through an alpha-spending approach using an O'Brien-Fleming-style boundary.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by framing the trade-off between early detection and error control, then propose a group sequential design with alpha spending (e.g., O'Brien-Fleming) and pre-specified interim looks. Explain how you would implement it in practice, including stopping rules for efficacy and futility, and how you would monitor sequentially without inflating type-I error.

Pro tip: Mention that you would pre-register the monitoring plan and simulate the design under the null and alternative to verify operating characteristics—this shows rigor and prevents p-hacking concerns.

1. Define the hypothesis and error control

State the null and alternative hypotheses, the overall type-I error rate (e.g., 5%), and the desired power. Emphasize that the family-wise error rate must be controlled across all interim looks.

2. Choose an alpha spending function

Select a spending function like O'Brien-Fleming or Pocock to allocate alpha across interim analyses. Explain that O'Brien-Fleming is conservative early and liberal later, which is often preferred for efficacy monitoring.

3. Schedule interim looks

Propose specific interim analysis points, e.g., at 25%, 50%, and 75% of planned sample size or information fraction. Discuss how the number and timing depend on the expected effect size and cost of data collection.

4. Define stopping rules

Specify efficacy boundaries (e.g., reject null if test statistic exceeds adjusted critical value) and futility boundaries (e.g., stop if conditional power falls below a threshold). Mention that futility can be non-binding to preserve type-I error.

5. Monitor and adjust sequentially

Describe the sequential monitoring process: after each interim look, compute the test statistic, compare to boundaries, and decide whether to continue, stop for efficacy, or stop for futility. Ensure that the spending function is followed exactly.

Key Points to Mention

  • Alpha spending functions (O'Brien-Fleming, Pocock) and how they control type-I error
  • Information fraction and its role in scheduling interim looks
  • Efficacy and futility stopping boundaries, and the difference between binding and non-binding futility
  • Simulation or software (e.g., gsDesign in R) to validate operating characteristics
  • Pre-registration of the monitoring plan to avoid bias
  • Trade-offs between number of interim looks, cost, and statistical power

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

Q4

What pre-experiment checks would you run before launching, and how would you handle potential interference between users and seasonality effects around weekends?

A/B Testing & ExperimentationAdaptability & Ambiguity
Author's notes

Covered the standard stuff: randomization check via a pre-experiment AA test, covariate balance across treatment and control, checking for holdout leakage if users share households or accounts.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Structure your answer by first outlining pre-experiment checks (e.g., sample size, randomization, instrumentation, guardrail metrics), then address interference and seasonality by proposing design and analysis solutions (e.g., cluster randomization, switchback tests, stratification, time-based controls). Emphasize proactive planning and robustness to real-world complexities.

Pro tip: Mention that you would pre-register the analysis plan and run a power analysis that accounts for potential interference and seasonality, and consider using a holdout group to measure long-term effects. This shows rigor and foresight.

1. Pre-experiment checks

Verify sample size and power, ensure proper randomization (e.g., check covariate balance), validate instrumentation and logging, and define guardrail metrics to monitor for unintended consequences.

2. Identify interference risks

Assess whether users interact (e.g., social networks, marketplaces) and if treatment can spill over. Consider cluster randomization or switchback designs to mitigate interference.

3. Address seasonality and weekend effects

Use stratification or blocking by day-of-week, include time fixed effects in analysis, or run experiments over full weeks to balance weekly patterns. Consider switchback tests to control for time-varying confounders.

4. Analysis and monitoring

Pre-register analysis plan, monitor for interference and seasonality during the experiment, and use appropriate statistical methods (e.g., CUPED, regression adjustment) to increase sensitivity.

5. Contingency planning

Have a plan if interference or seasonality is detected (e.g., extend duration, re-randomize, or use alternative designs). Communicate risks and trade-offs to stakeholders.

Key Points to Mention

  • Sample size calculation and power analysis
  • Randomization checks and covariate balance
  • Instrumentation and logging validation
  • Guardrail metrics and safety checks
  • Interference: cluster randomization, switchback tests, or holdout groups
  • Seasonality: stratification, time fixed effects, full-week experiments, or switchback designs

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

Q5

If a pure A/B test isn't possible due to legal or traffic constraints, what quasi-experimental design would you use instead, what assumptions does it rest on, and what would you show in your slides?

A/B Testing & ExperimentationTechnical Trade-offsProduct Analytics & Metrics
Author's notes

Proposed a regression discontinuity design on the score threshold since the treatment assignment is literally a cutoff.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by acknowledging the constraints and proposing a quasi-experimental design like difference-in-differences or synthetic control, tailored to the specific legal/traffic issue. Clearly state the key assumptions (e.g., parallel trends, no spillover) and how you would validate them. Then outline what you'd present in slides: design, assumptions, diagnostics, results with uncertainty, and sensitivity analyses.

Pro tip: Emphasize that you would pre-register the analysis plan and run placebo tests to build trust, since quasi-experiments are more susceptible to bias. Also, mention that you'd collaborate with legal and product teams early to ensure the design is feasible and compliant.

1. Clarify constraints and choose design

Identify the exact legal or traffic limitation (e.g., cannot randomize users, limited traffic in certain regions) and select a quasi-experimental method such as difference-in-differences, synthetic control, or regression discontinuity that fits the context.

2. State assumptions and validation plan

Explicitly list the assumptions (e.g., parallel trends, no interference, stable composition) and describe how you would test them (e.g., pre-trend checks, placebo tests, robustness checks).

3. Design the analysis and metrics

Define the treatment and control groups, the time periods, and the primary and guardrail metrics. Specify the statistical model and how you'll estimate the effect with confidence intervals.

4. Plan sensitivity and robustness checks

Outline additional analyses to assess how sensitive results are to violations of assumptions, such as varying the control group, using different time windows, or applying alternative estimators.

5. Structure the slide deck

Present the design rationale, assumptions, diagnostics (e.g., pre-trend plots), main results with uncertainty, sensitivity analyses, and a clear recommendation with caveats.

Key Points to Mention

  • Difference-in-differences (DiD) and its parallel trends assumption
  • Synthetic control method for constructing a counterfactual
  • Regression discontinuity design when there's a cutoff
  • Placebo tests and pre-trend validation
  • Sensitivity analysis to assess robustness
  • Clear communication of limitations and uncertainty in slides

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