← PlayStation Interview Insights

PlayStation·Data Scientist·Technical Phone Screen·Senior

Senior
Jun 2026

Summary

Senior DS interview at PlayStation, focused entirely on experimentation. Two meaty questions, both with follow-ups that kept branching. The social network effects one in particular had a lot of moving parts and I'm not sure I covered all of them well.

Questions Asked (2)

Q1

The experimentation platform ran an A/A test with an intended 50/50 split, but the observed ratio came out 51/49. Is that a problem, how would you test whether the imbalance is statistically meaningful, and what root causes would you dig into before trusting future A/B results?

A/B Testing & ExperimentationRoot Cause Analysis
Author's notes

My first instinct was to say 'no, that's fine, noise happens' and I think that's basically right but I fumbled the follow-up about how to actually test it.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by acknowledging that a 51/49 split in an A/A test is not necessarily a problem—random variation can produce such imbalances, especially with smaller sample sizes. Then outline a statistical test (e.g., chi-square goodness-of-fit) to determine if the deviation is significant, and finally discuss potential root causes like assignment bias, logging issues, or sample ratio mismatch (SRM) that could undermine future experiments.

Pro tip: Always check the sample ratio mismatch (SRM) before analyzing A/B test results; a significant SRM invalidates the experiment, so it's a critical sanity check. Mention that even a small imbalance can be problematic if it's statistically significant, as it suggests a systematic issue.

1. Assess the severity of the imbalance

Determine whether a 51/49 split is practically problematic by considering the sample size and the expected variability. A 1% deviation might be negligible in large samples but could indicate issues in smaller ones.

2. Test statistical significance

Use a chi-square goodness-of-fit test to compare observed counts to the expected 50/50 split. Calculate the p-value to see if the imbalance is statistically significant (e.g., p < 0.05).

3. Investigate potential root causes

If significant, dig into assignment mechanisms (e.g., randomization algorithm, hash function), data pipeline (e.g., logging errors, bot traffic), and external factors (e.g., user behavior, time zones) that could cause bias.

4. Evaluate impact on future experiments

Explain that a significant imbalance in an A/A test signals a flaw in the experimentation platform, which could lead to biased A/B results. Recommend fixing the root cause and re-running the A/A test before trusting future experiments.

Key Points to Mention

  • Sample ratio mismatch (SRM) and its importance as a validity check
  • Chi-square goodness-of-fit test for statistical significance
  • Randomization unit and assignment mechanism (e.g., user ID hashing)
  • Data logging and pipeline integrity (e.g., missing data, duplicate events)
  • Practical vs. statistical significance: consider effect size and sample size
  • Recommendation to fix root cause and re-validate with another A/A test

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

Q2

You want to test a new feature where friends can send each other virtual gifts, with the hypothesis that gifting increases engagement. Define your primary metric, guardrail metrics, and success criteria. Then walk through how you'd design the experiment, what randomization unit you'd pick, how your approach changes if the friendship graph is extremely dense, and what validity threats you'd be worried about.

A/B Testing & ExperimentationProduct Analytics & MetricsProduct Sense & Ideation
Author's notes

This one spiraled in a good way.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by clearly defining the primary metric (e.g., daily active friends gifting) and guardrail metrics (e.g., overall engagement, retention, and potential negative effects). Then outline a randomized controlled experiment, choosing an appropriate randomization unit (e.g., user or friendship) and addressing network effects if the friendship graph is dense. Finally, discuss validity threats like interference, novelty effects, and seasonality, and how to mitigate them.

Pro tip: When dealing with network effects, consider using cluster randomization or switchback designs to isolate the treatment effect. Also, pre-register your analysis plan to avoid p-hacking and ensure credibility.

1. Define Metrics and Success Criteria

Identify the primary metric (e.g., gifting rate or engagement lift) and guardrail metrics (e.g., retention, session time, or negative sentiment). Set a minimum detectable effect and success threshold based on business goals.

2. Design the Experiment

Choose a randomized controlled trial with a control and treatment group. Decide on the randomization unit (user, friendship, or cluster) based on the hypothesis and network structure. Plan sample size and duration.

3. Address Dense Friendship Graph

If the graph is dense, standard user-level randomization may cause interference. Consider cluster randomization (e.g., by community or friend group) or a switchback design to isolate effects.

4. Identify and Mitigate Validity Threats

Discuss threats like interference, novelty effects, seasonality, and selection bias. Propose solutions such as holdout groups, pre-period data, or statistical techniques like CUPED.

5. Analyze and Interpret Results

Use appropriate statistical tests, check for heterogeneous treatment effects, and ensure guardrails are not violated. Consider long-term holdout to measure sustained impact.

Key Points to Mention

  • Primary metric: e.g., increase in daily gifting actions or overall engagement (DAU/MAU).
  • Guardrail metrics: retention, session length, friend requests, or negative feedback.
  • Randomization unit: user-level for independent users, but cluster or friendship-level for dense graphs.
  • Network effects: interference can bias results; use cluster randomization or switchback.
  • Validity threats: novelty effect, seasonality, spillover, and SUTVA violations.
  • Statistical power: calculate sample size and duration to detect meaningful effect.

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