← Capital One Interview Insights

Capital One·Data Scientist·Technical Phone Screen·Senior

Senior
Jun 2026

Summary

Capital One data scientist interview with a pretty involved A/B testing case built around a nonprofit email campaign. The whole thing was one long multi-part problem that kept adding wrinkles, which I wasn't fully prepared for.

Questions Asked (5)

Q1

Define the primary success metric for the A/B test and at least two guardrail metrics that protect long-term program health. Justify each choice.

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

I went with conversion rate as the primary metric, which felt obvious, and then listed unsubscribe rate and spam complaint rate as guardrails.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by clarifying the business goal of the A/B test and how it maps to a measurable primary success metric that directly reflects the intended impact. Then select at least two guardrail metrics that capture potential negative side effects on long-term health, such as customer satisfaction or retention. Justify each metric by linking it to the company's strategic objectives and explaining how it balances short-term gains with long-term sustainability.

Pro tip: Choose guardrail metrics that are leading indicators of long-term value, not just lagging ones, and explicitly state thresholds for acceptable degradation to show you understand risk management in experimentation.

1. Clarify the test objective

Restate the hypothesis and the specific change being tested to ensure alignment on what success looks like. Identify the key business outcome the test aims to influence.

2. Define the primary success metric

Select a metric that directly measures the intended impact and is sensitive to the change. Justify why it is the best proxy for the business goal, considering factors like measurability and alignment with strategic KPIs.

3. Identify guardrail metrics

Choose at least two metrics that could be negatively affected by the change and are critical to long-term program health. Examples include customer retention, satisfaction (e.g., NPS), or operational efficiency.

4. Justify guardrail choices

Explain how each guardrail protects against unintended consequences and why it matters for long-term success. Link them to potential trade-offs and the company's risk tolerance.

5. Summarize and validate

Recap how the primary and guardrail metrics together provide a balanced view of success. Mention any statistical considerations, such as power or minimum detectable effect, to show rigor.

Key Points to Mention

  • Alignment with business KPIs and strategic goals (e.g., revenue, customer lifetime value)
  • Primary metric should be directly impacted by the change and measurable within the test duration
  • Guardrail metrics should include both customer experience (e.g., satisfaction, retention) and operational health (e.g., page load time, error rates)
  • Justification should address potential trade-offs between short-term gains and long-term value
  • Consideration of statistical power and sample size to detect meaningful changes in guardrails
  • Use of leading indicators (e.g., engagement) as guardrails to predict long-term effects

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

Q2

Calculate the minimum sample size per arm needed to detect a 10% relative lift over a 5% baseline conversion rate. Use a two-sided test at 95% confidence and 80% power. Show your formula and numeric result.

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

This is where I slowed down.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

First, clarify the parameters: baseline conversion rate (p1=0.05), relative lift of 10% gives p2=0.055. Then, use the standard formula for sample size per arm for a two-proportion z-test: n = ( (z_{α/2} + z_β)^2 * (p1(1-p1) + p2(1-p2)) ) / (p2 - p1)^2. Plug in z_{α/2}=1.96, z_β=0.84, and compute the result, rounding up to the next integer.

Pro tip: Mention that this is a simplified calculation assuming no continuity correction and equal arm sizes; in practice, you might adjust for unequal allocation or use exact methods, but this is standard for quick sizing.

1. Define parameters

Identify baseline conversion rate (p1=0.05), relative lift (10%), so p2 = p1 * 1.10 = 0.055. Also note significance level (α=0.05, two-sided) and power (1-β=0.80).

2. Determine critical values

For two-sided test at 95% confidence, z_{α/2} = 1.96. For 80% power, z_β = 0.84 (or 0.8416).

3. Apply sample size formula

Use n = ( (z_{α/2} + z_β)^2 * (p1(1-p1) + p2(1-p2)) ) / (p2 - p1)^2. Compute numerator and denominator separately.

4. Calculate numeric result

Plug in values: (1.96+0.84)^2 = 7.84; p1(1-p1)=0.0475; p2(1-p2)=0.051975; sum=0.099475; difference=0.005; squared=0.000025. n = (7.84 * 0.099475) / 0.000025 ≈ 31,195. Round up to 31,196 per arm.

5. Interpret and discuss assumptions

State that approximately 31,196 users per arm are needed. Mention assumptions: independent observations, no continuity correction, equal variance approximation.

Key Points to Mention

  • Baseline conversion rate and relative lift conversion to absolute difference
  • Two-sided test and corresponding z-value (1.96)
  • Power and z-value for beta (0.84)
  • Sample size formula for two proportions
  • Rounding up to ensure sufficient sample
  • Assumptions and potential adjustments (e.g., continuity correction, unequal allocation)

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

Q3

How would you segment results by donor tier (high vs. low value) without inflating false positives? Describe your multiple testing or hierarchical modeling approach.

A/B Testing & ExperimentationData Modeling
Author's notes

I brought up Bonferroni as the simple answer, then mentioned that hierarchical modeling lets you borrow strength across tiers which is more appropriate when segments are small.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by acknowledging the multiple testing problem when segmenting by donor tier, then propose a hierarchical Bayesian model that partially pools information across tiers to control false positives. Alternatively, discuss pre-registering tier-based hypotheses with appropriate corrections like Bonferroni or FDR, and emphasize the trade-off between power and false discovery. Conclude with how you'd validate results via simulation or holdout.

Pro tip: Mention that hierarchical models are especially useful when tier sizes are imbalanced—high-value donors are few, so borrowing strength from the overall population reduces variance without inflating false positives. Also, note that pre-registration of tier hypotheses is key to avoid p-hacking.

1. Identify the multiple testing risk

Explain that segmenting by donor tier creates multiple comparisons (e.g., high vs. low), increasing family-wise error rate. Emphasize the need to control false positives.

2. Choose a correction or modeling strategy

Present options: frequentist corrections (Bonferroni, Holm, FDR) or hierarchical Bayesian models. Discuss when each is appropriate, noting hierarchical models are better for small subgroups.

3. Detail the hierarchical modeling approach

Describe how partial pooling across tiers estimates tier-specific effects while shrinking extreme estimates toward the overall mean, reducing false positives. Mention priors and hyperpriors.

4. Validate with simulation or holdout

Propose simulating data under the null to check false positive rates, or using a holdout set to confirm findings. This demonstrates rigor.

5. Communicate trade-offs and business implications

Summarize how the chosen method balances false positives and power, and how it informs decisions about donor tiers. Highlight interpretability for stakeholders.

Key Points to Mention

  • Multiple testing problem and family-wise error rate (FWER) or false discovery rate (FDR)
  • Hierarchical Bayesian models with partial pooling to borrow strength across tiers
  • Bonferroni, Holm, or Benjamini-Hochberg corrections as frequentist alternatives
  • Pre-registration of tier-specific hypotheses to avoid p-hacking
  • Simulation-based calibration to assess false positive control
  • Trade-off between statistical power and false positives, especially with small high-value tier

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

Q4

Describe a stopping rule for the experiment and explain the risks of peeking at results early. How would you handle uneven email deliverability across donor segments?

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

Peeking question is pretty standard and I handled it fine.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by defining a stopping rule based on statistical power and business constraints, then explain the risks of peeking (inflated Type I error, biased estimates). Finally, address uneven email deliverability by proposing segment-level analysis and adjustments like stratification or weighted metrics.

Pro tip: Mention sequential testing or alpha-spending as a rigorous alternative to fixed-horizon tests if stakeholders insist on early looks, and emphasize pre-registration of the stopping rule to avoid p-hacking.

1. Define the stopping rule

Specify a fixed sample size or duration based on power analysis, and state that the experiment will stop only when that criterion is met. Optionally, mention sequential testing methods if early stopping is required.

2. Explain risks of peeking

Describe how repeated looks at accumulating data inflate the false positive rate and lead to biased effect estimates. Emphasize that peeking without correction undermines the validity of the test.

3. Address uneven email deliverability

Acknowledge that deliverability differences across segments can confound results. Propose analyzing results within segments, using stratification, or weighting to ensure balanced comparisons.

4. Propose mitigation strategies

Suggest techniques like inverse probability weighting, propensity score adjustment, or running separate experiments per segment if deliverability issues are severe.

5. Summarize and connect to business impact

Tie the technical solutions back to reliable decision-making, ensuring that conclusions are valid and actionable for the business.

Key Points to Mention

  • Fixed-horizon testing and power analysis
  • Alpha inflation and Type I error from peeking
  • Sequential testing / alpha-spending functions
  • Stratified randomization or analysis
  • Inverse probability weighting (IPW) for deliverability
  • Pre-registration of analysis plan

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

Q5

If Variant B increases conversion rate but reduces average gift size by 5%, how do you reframe the decision using net revenue per reached recipient? Show the calculation.

A/B Testing & ExperimentationPricing & MonetizationProduct Analytics & Metrics
Author's notes

This was my favorite part of the whole case because it forced you to stop treating conversion rate as the end goal.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Reframe the decision by calculating net revenue per reached recipient for both variants, incorporating the conversion rate and average gift size. Compare the net revenue per recipient to determine which variant yields higher overall revenue, considering the trade-off between conversion and gift size. Show the calculation clearly and discuss implications for statistical significance and business goals.

Pro tip: Always tie the metric back to the business objective—here, net revenue per recipient directly aligns with profitability. Also, mention that you'd validate the result with a confidence interval to ensure the difference isn't due to chance.

1. Define the metric

Net revenue per reached recipient = conversion rate × average gift size. This metric captures both the likelihood of conversion and the value of each conversion.

2. Set up the calculation

Assume baseline values for Variant A (e.g., conversion rate = c, average gift = g). For Variant B, conversion rate increases by some percentage (e.g., +x%), and average gift decreases by 5% (so new gift = 0.95g).

3. Compute net revenue per recipient

For Variant A: R_A = c × g. For Variant B: R_B = (c × (1 + x/100)) × (0.95g). Simplify to R_B = 0.95 × (1 + x/100) × c × g.

4. Compare and decide

Compare R_B to R_A. Variant B is better if 0.95 × (1 + x/100) > 1, i.e., if the conversion lift exceeds approximately 5.26% (since 1/0.95 ≈ 1.0526). Otherwise, Variant A yields higher net revenue per recipient.

5. Discuss statistical and practical significance

Even if R_B > R_A, check if the difference is statistically significant and practically meaningful. Consider confidence intervals and potential long-term effects on customer lifetime value.

Key Points to Mention

  • Net revenue per reached recipient as the key metric for decision-making.
  • The trade-off between conversion rate and average gift size.
  • The break-even conversion lift needed to offset a 5% drop in gift size (≈5.26%).
  • The importance of statistical significance testing to validate the observed difference.
  • Consideration of other metrics like total revenue, customer lifetime value, and long-term impact.
  • Clear communication of assumptions and calculations to stakeholders.

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