Interview guides · Eightfold

Eightfold Data Scientist Interview Questions & Guide 2026

Eightfold data scientist prep on data pitfalls: selection bias, target leakage, and checking an outlier's provenance before you drop it.

The 60-second brief

As a Data Scientist at Eightfold, you play a pivotal role in harnessing data to drive strategic decisions and enhance user experiences. Your work involves analyzing complex datasets to uncover insights that inform product development and operational efficiency. This position is crucial, as it directly impacts the effectiveness of Eightfold's AI-driven solutions, which aim to match talent with opportunities, ultimately shaping the future of work.

SQL is seldom the hardest round and is often the one that eliminates people. The working bar is usually window functions, correct deduplication, and joins that do not silently fan out rows, rather than obscure syntax.

Focus areas

Pick a randomisation unit that respects interference
Size an experiment before anyone launches it
Separate novelty effects from durable behaviour change

Overview

In this role, you will collaborate with cross-functional teams, including engineering and product management, to develop algorithms and models that enhance the capabilities of Eightfold's platform. The projects you undertake will vary in scale and complexity, providing you with the opportunity to work on innovative solutions that address real-world challenges. As a Data Scientist, your contributions will not only influence products but also help to define the strategic direction of Eightfold, making this position both rewarding and impactful.

The Eightfold interview process

Eightfold candidates report 4 rounds · ≈ 3-5 weeks. The stages below are what candidates describe, not a published process.

Resume Review

Whoever runs this call is usually not a practitioner. They take notes, and a hiring manager skims those notes later, so the real question is whether your work survives being written down by someone outside the field. Test every project sentence against that: could a non-specialist repeat it correctly without knowing what a propensity score is? Carry a plain-language version of each project and one reason you want this particular role that you could not copy onto another application. Vagueness at this stage reads as inexperience, even when the underlying work was genuinely deep.

What to demonstrate

Whether a non-specialist can restate your projects accurately, since their paraphrase is what reaches the hiring manager
Whether your reason for wanting the role points at the work itself rather than the company's reputation
Whether your language signals the level being screened for: what you decided yourself versus what you were handed

How to prepare

Write a two-sentence, jargon-free version of each major project: the question nobody could answer, and the decision your work changed. Read it to someone outside data and have them repeat it back
Point your 'why this role' answer at something concrete in the job description or the product surface you would be working on, and keep it to two sentences
Have two questions ready about measurement: which metric the team is held to, and who acts on an analysis once it lands

Technical Assessments

Before anything else, this round is a reading test. You are given a small schema and a question phrased in business language, and most of the difficulty sits in the gap between them. Who counts as an active user, does a refunded order still count as an order, is that date column an event time or a load time. Weak answers start typing immediately and compute something precise about the wrong population. Strong ones pin the definition in one sentence, name the column that encodes it, then write the query. On a timed assessment with nobody to tell, write the definition in a comment anyway.

What to demonstrate

Whether an ambiguous term becomes a specific column and filter before any computation happens
Whether you read the schema for keys and cardinality rather than only for column names
Whether the result answers the question at the grain it was asked at, per user or per session or per day

How to prepare

Take three metrics you already use and write down the exact filter and exact grain behind each, then practise stating one of them in a single sentence out loud
On a schema you have never seen, spend the first minute writing what one row of each table means and which key it is unique on, then predict which joins can duplicate rows
Rehearse a version where the definition changes halfway through, and edit the query you have instead of starting over

Homework Assignment

A take-home is graded as an argument, not as a notebook. Somebody reads the submission without you in the room, so every choice has to survive on the page: why the question was framed this way, and what was deliberately left out. The gap between a strong and a weak submission is almost never model quality. It is whether the writeup names the specific question it answers and commits to a recommendation, including what evidence would overturn it. A high-accuracy model attached to no conclusion reads as effort that stopped before the decision.

What to demonstrate

Whether the question you answered is stated outright, and whether it is the question the prompt posed rather than an easier neighbour of it
Whether the recommendation is specific enough to act on, with the uncertainty attached to it instead of parked in a caveats section at the end
Whether analytical choices such as the metric definition, the population filter and the time window are justified in the prose, not merely visible in code

How to prepare

Take a dataset you have already worked with, write the one-paragraph conclusion first, then check whether the analysis you were planning actually supports it and cut whatever does not
Practise stating a metric in one sentence that fixes the population, the time window and the denominator, then confirm your query computes exactly that sentence and nothing adjacent to it
Hand a draft to someone outside the problem and ask them to tell you back what you recommended and why; anything they cannot recover is not on the page yet

Cultural Fit Interviews

An added round often puts you in front of someone outside the core hiring team: a partner engineer, a product owner, a domain expert, sometimes a more senior manager. The question they are really asking is not whether you can do the work but whether they would trust a number that came from you. That changes what a good answer looks like. Lead with what the decision cost and what it changed, keep the method available but not central, and be plain about the limits of your evidence. Overstating a result is the fastest way to lose this round.

What to demonstrate

Whether you can explain a technical choice to someone who will never read your code, without either flattening it into nothing or hiding inside jargon
Honesty about evidence strength: what the analysis establishes, what it only suggests, and what it cannot say at all
How you take disagreement, specifically whether you update on a good objection, hold your position with reasons, or fold on contact

How to prepare

Write the two-sentence version of your most technical project for a non-specialist, then check that neither sentence needs a method name to make sense.
For one result you are proud of, write the strongest objection someone could raise and a response that concedes the part of it that is correct.
Prepare one decision that turned out to be wrong: how you found out, what it cost, and what you changed afterwards. A senior cross-functional interviewer asks for this more often than a technical one does.

Where candidates lose points

Comparing cohort retention curves of different maturities, or building the curve from users who are still present

A cohort four weeks old has no week-8 value, so an average taken across cohorts silently drops young cohorts from the later columns and keeps them in the earlier ones. The curve then bends upward at the tail, and the reading that 'retention is improving over time' is an artefact of which cohorts survived to be measured. The same error appears in the denominator when retention is computed over users active in the current period rather than over the full original cohort, which conditions on survival and guarantees a flattering number. The fix is a triangle: fix the cohort at signup, bound every window on both sides, and only compare cells where every cohort has had the full elapsed time, publishing the rest as blank rather than as a partial average.

Slicing a flat experiment until a segment reaches significance

Testing one metric across twenty segments at a nominal 5% level produces a significant result about two thirds of the time when nothing is happening anywhere, and the segment that surfaces is by construction the one with the most favourable noise. The reported effect in that slice is then badly overstated, because selection on significance conditions the estimate on being large. What makes it dangerous rather than merely wrong is that a post-hoc segment always has a plausible story attached, so it survives the meeting. The controls are declaring the small number of segments of interest before launch, correcting across the ones tested, and treating anything discovered afterwards as a hypothesis that needs its own adequately-powered test rather than a finding.

Reading a dozen metrics with no multiplicity control

Nominate one primary metric before launch and treat the rest as guardrails or exploratory, with Bonferroni or Benjamini-Hochberg applied when you intend to make claims from them. Twenty independent tests at 0.05 under the null produce at least one false positive about 64 percent of the time.

Crediting a treatment for regression to the mean

Selecting a group because it is extreme (lowest-engagement users, accounts having their worst month, the bottom decile of a score) moves that group's expected next-period value back toward the average even under no treatment, by exactly as much as the selecting measure is imperfectly correlated with its own later value. Compare against units that met the same selection rule and went untreated, or use two pre-periods so the bounce-back is visible before the intervention starts. A pre-post number on a group chosen for being extreme measures the selection rule, not the treatment.

Questions & practice

Write a function to calculate the mean and standard deviation of a list.

Medium · statistics and probability

Approach

Translate the result into the decision it informs, in one plain sentence.
Quantify uncertainty explicitly rather than reporting a point estimate alone.
Write down the assumption the method needs before you use the method.

Follow-up

What sample size would you need to detect an effect half this size?
Which assumption here is most likely to be violated in practice?

Describe the bias-variance tradeoff.

Medium · statistics and probability

Approach

Quantify uncertainty explicitly rather than reporting a point estimate alone.
Write down the assumption the method needs before you use the method.
Translate the result into the decision it informs, in one plain sentence.

Follow-up

Which assumption here is most likely to be violated in practice?
How would you explain this result to someone who does not know statistics?

How would you approach a situation where your model is underperforming?

Medium · machine learning and modelling

Approach

Check what information would not exist at prediction time, and exclude it.
Pick an evaluation metric that matches the cost of each error type, not a default.
Set a baseline first, so any model has something honest to beat.

Follow-up

Where could label leakage enter this setup?
What would you monitor after launch to know the model is still valid?

What are some common algorithms used in classification tasks?

Medium · machine learning and modelling

Approach

Frame the prediction: the label, the moment of prediction, and the action it triggers.
Set a baseline first, so any model has something honest to beat.
Say how the offline result would be validated online before it is trusted.

Follow-up

Where could label leakage enter this setup?
How would you choose the decision threshold, and who owns that choice?

Rebuild per-visitor ordering without groupby convenience methods

Easy · pandas · vectorisation · window logic

You have a DataFrame of 2 million fct_event rows with visitor_id, occurred_at_utc and event_id, unsorted and containing duplicate timestamps within a visitor. Produce three new columns: event_rank, the 1-based position of the event within its visitor ordered by occurred_at_utc; seconds_since_prev, the gap to that visitor's previous event, NULL for the first; and is_first_for_visitor. You may use sort_values, shift, cumsum, numpy and boolean masking. You may not use groupby.transform, groupby.apply, groupby.cumcount, groupby.rank or merge_asof. Break timestamp ties on event_id.

Approach

Sort once by ['visitor_id', 'occurred_at_utc', 'event_id'] and reset the index. The whole exercise reduces to row arithmetic on a sorted frame, and the tiebreak on event_id is what makes the result reproducible across runs.
Mark visitor boundaries with is_first = df['visitor_id'].ne(df['visitor_id'].shift()). This is the single fact every other column derives from.
Compute seconds_since_prev as the diff of the timestamp column, then overwrite it with NaT/NaN wherever is_first is True. The shift crosses the boundary between visitors and will otherwise hand the first row of each visitor the last event of the previous one.
Build event_rank from a running counter that resets at boundaries: take a global cumulative position (np.arange(len(df))) and subtract, per row, the global position at which that visitor started. Get the start position by forward-filling the positions where is_first is True, which is a cumsum-free reset and is O(n).
Verify against the forbidden method once, as a test rather than as the implementation, and confirm the two agree on every row.

Worked solution (20 min)

Sort on the three-key tuple and reset_index(drop=True).
Compute is_first via .ne(.shift()), which is True for row 0 because the shifted value is NaN.
pos = np.arange(len(df)); start = pd.Series(np.where(is_first, pos, np.nan)).ffill(); event_rank = (pos - start + 1).astype(int).
gap = df['occurred_at_utc'].diff().dt.total_seconds(); gap[is_first] = np.nan.
Assert event_rank equals df.groupby('visitor_id').cumcount() + 1 on the sorted frame.

Expected result: Three columns on the sorted frame: event_rank starting at 1 for every visitor and increasing by 1 with no gaps, seconds_since_prev null exactly where is_first_for_visitor is True, and is_first_for_visitor summing to df['visitor_id'].nunique().

Verify it yourself

is_first_for_visitor.sum() equals the number of distinct visitor_id values.
seconds_since_prev.isna().sum() equals that same number.
event_rank.max() per visitor equals that visitor's row count, and event_rank is non-negative everywhere.
A visitor with two events at the identical timestamp gets ranks 1 and 2 with a gap of 0.0, ordered by event_id.

Follow-up

The frame does not fit in memory. How does your approach change if you can only process one visitor-partitioned chunk at a time?
occurred_at_utc is client-supplied and sometimes runs backwards within a visitor. Does your seconds_since_prev go negative, and should it?
How would you extend this to reset the counter at every change of surface as well as visitor?

Can you explain the time complexity of your solution?

Medium · sql and data manipulation

Approach

Say which table is the grain you start from, and join outward from it.
Handle the rows that do not match: a LEFT JOIN with a NULL check is usually the question.
State the window function and its partition and ordering out loud before writing it.

Follow-up

How does the query change if the join becomes one-to-many?
What breaks if events arrive late or out of order?

Weekly visit-to-signup conversion split by acquisition channel

Easy · funnel · conversion · aggregation

From fct_session (session_id, visitor_id, started_at_utc, referrer_channel, is_bot_flagged, consent_state) and fct_event (visitor_id, occurred_at_utc, event_name), compute visit-to-signup conversion for one ISO week, split by channel. session_id is the unique key of fct_session. Denominator: distinct visitor_id with a session starting in the week, is_bot_flagged = FALSE and consent_state <> 'denied'. Numerator: those visitors with a 'signup_completed' event in the same week. Label each visitor with the referrer_channel of their first session in the window. Return channel, visitors, signups and rate, plus one all-channel total row.

Approach

Build a visitor spine that is one row per visitor: filter sessions to the week, drop is_bot_flagged and consent_state = 'denied', then take the first session per visitor with ROW_NUMBER() OVER (PARTITION BY visitor_id ORDER BY started_at_utc, session_id) = 1 to carry the channel label. Collapsing to one row here is what makes the channel buckets mutually exclusive and the totals additive.
session_id is the unique key, so that ordering is total and the label is reproducible. If the table carried no unique key you would have to write an explicit tie rule instead, because two sessions on different channels at the identical timestamp would otherwise label the visitor differently between runs.
Attach the outcome as a semi-join (EXISTS on a signup_completed event for that visitor inside the same week) rather than a join to the event table, so a visitor who fires the event twice does not count twice and inflate the numerator past the denominator.
Aggregate with COUNT() as visitors and COUNT() FILTER (WHERE signed_up) as signups, and compute the rate as signups::numeric / NULLIF(visitors, 0) so an empty channel returns NULL rather than a division error.
Produce the total with GROUP BY GROUPING SETS ((channel), ()), which re-sums numerator and denominator for the total row. Averaging the channel rates gives a different and wrong number whenever channel volumes differ, which they always do.
Verify the spine before trusting the output: COUNT(*) must equal COUNT(DISTINCT visitor_id), and the per-channel visitor counts must sum to the total row.

Worked solution (20 min)

Write the filtered session CTE and check its row count against an unfiltered count, so you know how much volume the bot and consent filters removed.
Add the ROW_NUMBER first-session pick and assert one row per visitor.
Add the EXISTS outcome flag and aggregate with FILTER.
Add GROUPING SETS for the total and format the rate to four decimal places.
Spot-check one channel by hand: pull its visitor list, count signups directly, compare.

Expected result: One row per referrer_channel plus a total row, with visitors, signups and a decimal rate. Channels with zero signups appear with rate 0, not missing. The total rate lies strictly between the minimum and maximum channel rate unless one channel holds all the volume.

Verify it yourself

Per-channel visitor counts sum exactly to the total row's visitor count.
COUNT(*) equals COUNT(DISTINCT visitor_id) on the spine CTE.
Replacing the EXISTS with a plain inner join changes the signup count only if duplicate signup_completed events exist; if it does change, say by how much.
Every rate is between 0 and 1.
Re-running the first-session pick with session_id removed from the ORDER BY returns the same labels; if it does not, visitors hold same-timestamp sessions on different channels and the tie rule is doing real work.

Follow-up

The denominator is distinct visitors. If a browser release shortens cookie lifetime, what happens to this rate, and how would you tell that apart from a genuine drop?
A visitor's first session is direct and their signup session is paid search. Your label says direct. When is that the wrong answer for the decision being made?
How do you roll four weeks into a month, and why is averaging the four weekly rates wrong?

How do you prioritize tasks when managing multiple projects?

Medium · product sense and metrics

Approach

Decompose the metric into the rates that drive it, and say which one you would check first.
State what result would change your recommendation, so the answer is falsifiable.
Restate the decision this analysis has to support, and who acts on the answer.

Follow-up

What would you do if the primary metric and the guardrail moved in opposite directions?
How would you detect that the metric is being gamed rather than genuinely improving?

If given a dataset with missing values, what strategies would you employ to handle it?

Medium · product sense and metrics

Approach

Fix the population and the time window before naming any metric.
Decompose the metric into the rates that drive it, and say which one you would check first.
Name one primary metric, then the guardrail that stops it being gamed.

Follow-up

What would you do if the primary metric and the guardrail moved in opposite directions?
How would you detect that the metric is being gamed rather than genuinely improving?

What attracts you to working at Eightfold?

Medium

Approach

Clarify what is being asked and what a complete answer would contain.
State your assumptions explicitly before working the problem.
Say what you would check first and why it is the highest-information step.

Follow-up

What assumption would you test first?
How would you know your answer was wrong?

Diagnose a 50.5 to 49.5 split before reading the result

Easy · sample ratio mismatch · exposure logging · chi-square

An experiment randomised on visitor_id ran for 11 days. fct_experiment_exposure holds 104,320 control rows and 102,180 treatment rows for the experiment_id, all with is_in_analysis_population = TRUE, against a configured 50/50 split. The treatment arm shows a 3.1% relative lift in visit-to-signup conversion at p = 0.004, and the team wants to ship. Decide whether that lift can be reported, show the arithmetic behind your decision, and name the three checks you would run first on the exposure logging.

Approach

Test the split instead of eyeballing it. Chi-square goodness of fit against 103,250 expected per arm gives 2 x 1070^2 / 103,250 = 22.2 on 1 degree of freedom, p about 2.5e-6. The conventional alarm threshold is p < 0.001, so this is a sample ratio mismatch.
Treat the mismatch as invalidating, not as a caveat. The arms are no longer exchangeable, so the 3.1% lift has no causal reading and rebalancing on covariates afterwards does not restore it.
Walk the logging path in the order units flow through it: assignment service, then the exposure event fired on the treated surface, then the filters that build the analysis population. Each stage can drop one arm preferentially.
Name the three suspects this stack actually has. Exposure emitted by client code the treatment arm reaches later or not at all when its bundle errors; an extra redirect or render in one arm that loses slow connections; and a post-assignment filter (is_bot_flagged, is_internal, consent_state) that correlates with variant.
Check whether the imbalance is uniform by splitting counts on session_date, surface, app_version and device_type. A mismatch confined to one client build or to day one points at a deployment fault that can be fixed and re-run, not at a design fault.

Worked solution (15 min)

N = 206,500, expected 103,250 per arm, observed deviation 1,070, which is 0.518% of the total pushed into one arm.
Chi-square = 2 x 1070^2 / 103,250 = 22.18 on 1 df, p about 2.5e-6.
Compare with the p < 0.001 threshold and stop: the readout is void.
Re-pull the same counts grouped by session_date and app_version to localise where the rows were lost.
Deliver one line: the split is off by 1,070 visitors, a roughly one-in-400,000 event under correct randomisation, so the experiment is being fixed and re-run rather than read.

Expected result: Chi-square(1) = 22.2, p about 2.5e-6, far past the p < 0.001 mismatch threshold. The correct deliverable is an exposure-logging investigation and a re-run, not a caveated 3.1% lift.

Verify it yourself

Cross-check the statistic as a z on one arm count: under a fair split that count has SD sqrt(N/4) = sqrt(51,625) = 227 visitors, so the 1,070 deviation is 4.71 SD, and 4.71^2 = 22.2 reproduces the chi-square.
Chi-square scales linearly with N at a fixed ratio, so the same 50.518% split at N = 2,000 returns 22.18 / 103.25 = 0.21, p = 0.64. That reconciles the arithmetic and nothing more; it is not evidence that the alarm is independent of N. What rules out the large N is that the p-value is uniform under correct randomisation at every sample size, so p = 2.5e-6 is a one-in-400,000 draw whether N is 2,000 or 2,000,000. Large N buys the power to resolve a 0.5% skew; it does not manufacture one.
The mismatch p-value should be orders of magnitude smaller than the lift's p-value; if they are comparable, recheck the arithmetic.
Arm counts must sum to the total exposure rows for that experiment_id. If they do not, the analysis-population filter is already dropping rows before you looked.

Follow-up

The imbalance is entirely in one app_version on android. Can you salvage the other surfaces, and under what argument?
How would you monitor this across every running experiment without drowning in false alarms from a daily chi-square at alpha 0.05?
The missing rows turn out to be disproportionately visitors with consent_state = 'unknown'. What does that do to the estimate even after the logging bug is fixed?

Pooled signup conversion fell while every segment rose

Medium · mix-shift · simpsons-paradox · decomposition

Weekly visit-to-signup conversion, counted on distinct fct_session.visitor_id with is_bot_flagged = TRUE and consent_state = 'denied' sessions excluded, fell from 4.4% to 3.9% week over week. Split by device_type and referrer_channel, all twelve cells are flat or up. A paid_social campaign launched on Monday. Using fct_session and fct_event, quantify how much of the 0.5-point fall is mix and how much is within-segment rate, then state what you would tell the growth lead.

Approach

Write the pooled rate explicitly as the sum over segments of weight times segment rate, and materialise both weeks' weights and rates into one table. Until that table exists there is nothing to decompose, only opinions.
Compute three quantities and report all three: the rate effect holding the prior week's weights fixed, the mix effect holding the prior week's rates fixed, and the interaction residual. Reporting only the first two hides a term that can be material when both weights and rates move a lot.
Rank segments by their individual mix contribution, computed as the change in that segment's weight multiplied by its prior-period rate. This is what lets you say one cell caused the move rather than gesturing at the campaign.
Verify the new traffic is human and countable before accepting the mix story: check is_bot_flagged coverage on the new channel, the distribution of duration_seconds and event_count for its sessions, and whether its consent_state profile differs from the rest.
Deliver the conclusion as a definition change rather than a diagnosis: a pooled rate over a mix that moves is not comparable week over week, so the recurring report should carry per-channel rates plus absolute signups, with the pooled figure demoted or dropped.

Follow-up

Paid social converts at roughly a quarter of organic but absolute signups rose. Is the campaign working, and what would you need to answer that properly?
Would you reach the same conclusion if the campaign had moved the mix by two points instead of sixteen? Where is your threshold and why?
How would you present this to someone who has been watching the pooled number in a weekly meeting for a year?

Suggested practice checklist

For a candidate whose interviews will centre on A/B testing, metric movement and causal claims. Design comes before arithmetic, arithmetic before analysis, and the week ends by rehearsing the readout rather than the derivation.

Day 1 — Design one test end to end on paper

Take a single feature change and write the full design: randomization unit, the exact point of exposure, the primary metric with its grain, guardrails, allocation, planned duration, and the decision rule committed before any data exists.
Write why the randomization unit must sit at or above the level where treatment can spill over, and give one case where user-level randomization is still contaminated (shared accounts or devices, or two participants in the same marketplace).
State in advance what you will do if the primary metric is flat while a secondary metric is significant.

Deliverable: A one-page test design with a decision rule written before launch.

Day 2 — Power arithmetic until it is automatic

Compute required sample size per arm for a binary metric with the normal approximation, n is approximately 2 times (z for alpha/2 plus z for power) squared times p(1 minus p) divided by delta squared, for baselines of 2, 10 and 40 percent at a 5 percent relative lift, and note that for a fixed relative lift the requirement falls as the baseline rises because delta grows proportionally with p.
Redo the calculation for a continuous metric using variance in place of p(1 minus p), and show why a heavy-tailed quantity such as revenue per user needs either far more traffic or a capped version with a stated cap.
Convert one of the results into weeks given a weekly eligible traffic figure, then list the two honest ways to shorten it (accept a larger detectable effect, or reduce variance) and write why quietly lowering the power target is a decision to miss more real wins, not a speedup.

Deliverable: A small script or sheet that maps baseline, minimum detectable effect, alpha and power to sample size and weeks, cross-checked against a published calculator.

Day 3 — Variance and the unit-of-analysis problem

Take a ratio metric whose denominator is not the randomization unit (clicks per session, randomized by user) and compute the standard error twice, once naively at session level and once by the delta method or a user-level bootstrap, then record how much the naive version understates it.
Implement CUPED on simulated data: choose a pre-period covariate X measured before assignment, estimate theta as Cov(Y, X) divided by Var(X), and analyse Y minus theta times (X minus its mean) in place of Y. Confirm the variance of the adjusted outcome equals the raw variance multiplied by one minus the squared correlation between Y and X, so a correlation of 0.45 removes about 20 percent of the variance and not 80.
Now run that simulation a few hundred times and confirm the adjusted effect estimate is unbiased for the same effect rather than numerically identical to the raw one. Within any single run the two differ, sometimes by a large fraction of the true effect, because the two arms' pre-period covariate means never coincide exactly in a finite sample; they agree in expectation, which is the property that matters and the one to state out loud.

Deliverable: A notebook showing the adjusted estimator with a measurably smaller variance than the raw one, plus a repeated-simulation table showing the two estimators agreeing on average while differing run by run.

Day 4 — Validity threats you can actually test for

Run a sample ratio mismatch check as a chi-square goodness-of-fit test against the intended allocation, and write the three causes you would chase first (assignment logged before exposure, an arm-specific redirect or load failure, bot filtering applied asymmetrically).
Simulate peeking: generate A/A data, test daily at alpha 0.05 across 14 looks, record the inflated false positive rate, then apply an alpha-spending boundary or commit to a fixed horizon and confirm the rate returns to nominal.
Write how you would separate a novelty effect from a durable lift using the treatment effect plotted against days since first exposure, and what shape would change your recommendation.

Deliverable: One table showing the peeking false positive rate before and after correction, plus a written SRM triage list.

Day 5 — When randomization is not available

Write the identifying assumption for difference-in-differences (parallel trends in the absence of treatment), then plot pre-period trends for two candidate control groups and justify rejecting one of them.
Design a switchback test for a change where user-level randomization would leak across participants, choosing a time-block length against the carryover you expect and saying how you would detect carryover in the data.
List what an interrupted time series or a synthetic control buys you and the one thing neither can rule out: an unobserved shock that coincides with the launch.

Deliverable: A one-page memo recommending a single quasi-experimental design and naming its weakest assumption explicitly.

Day 6 — The readout query

Write the assignment-to-exposure join that returns exactly one row per unit per experiment, and handle units appearing in both arms by excluding and counting them rather than silently keeping one.
Compute the per-arm metric, its variance and the relative lift with a confidence interval in SQL, then reproduce the identical numbers in a notebook as a cross-check.
Add a segment breakdown and write the sentence that keeps it from being p-hacking: segments declared in advance, everything else reported as exploratory and corrected for multiplicity.

Deliverable: A single query that outputs the full readout table, matched to a notebook recomputation.

Day 7 — Present it to someone who will not read the appendix

Give a 10-minute readout of a real or simulated experiment in the order decision, number, uncertainty, caveat.
Have your listener ask "can we ship it" in the case where the primary is flat and a guardrail moved, and answer with a recommendation rather than a request for more data.
Rewrite your opening line so the recommendation lands before any methodology.

Deliverable: A one-page readout whose first line is the recommendation.

Your part, not the team's

Most data work is done by groups, so an interviewer has to work out which piece was yours. An answer that runs on 'we' for several minutes gets interrupted with a question about what you personally did, and by then the answer sounds defensive even when it is true. Mark your own contribution as you go, and name the parts that belonged to someone else instead of leaving them ambiguous. Keep a few specifics back as well, like the name of the metric or who actually objected, so a probe can be answered with something you had not already said.

Discuss a time you had to influence stakeholders to adopt your recommendations.

Medium · behavioural and stakeholder questions

Approach

State the situation in two sentences and spend the rest on your reasoning.
Close with what you would do differently, concretely.
Quantify the outcome, including what you would not claim credit for.

Follow-up

How did you know the outcome was caused by your change?
What would you do differently if you ran that project again?

Turn an ambiguous onboarding question into a measurable metric

Easy · scoping · metric definition · stakeholder

Two days before a planning review, a director asks whether onboarding is working. You have dim_user (account_created_at_utc, signup_surface, is_internal), fct_event (is_core_action, flow_id, flow_instance_id, event_name, occurred_at_utc, received_at_utc) and fct_session. No further meeting with the director is possible before you start work. Deliver three clarifying questions you would send in writing, the metric you will compute in the meantime with its numerator, denominator, window and exclusions, and one sentence naming the question you are deliberately not answering.

Approach

Recognise what is being probed: whether you convert a goal into a computable predicate without stalling for requirements or guessing in silence. Listing clarifying questions is the generic answer; shipping a defensible default alongside them is the strong one, because the review is in two days and it will happen with or without you.
Infer the decision behind the request. A question about whether onboarding works, arriving before a planning cycle, usually means whether to staff it next quarter. That points at a rate with visible headroom over several cohorts, not at a descriptive dashboard.
Write the three questions so that each one changes the SQL. Which population, all signups or only self-serve from dim_user.signup_surface. What counts as working, reaching a core action or completing the onboarding flow_id. Against what bar, last quarter's cohorts or a stated target.
Propose the default explicitly: seven-day activation on weekly signup cohorts. Numerator, users with is_core_action = TRUE events on at least two distinct UTC dates inside [account_created_at_utc, account_created_at_utc + 7 days). Denominator, the signup cohort with is_internal = FALSE. Publish with an eight-day lag, and state that the two-distinct-days threshold is a frozen choice rather than a discovery.
Name the exclusion in the same breath as the number. The series shows whether users activate; it does not establish that onboarding caused the level, which needs a staged rollout or an experiment.

Follow-up

The director replies that they meant the onboarding flow specifically, not activation. What changes in the query and in the caveats?
Your cohort metric needs an eight-day lag and the review is in two days. What do you present, and how do you label it?
Two of your three questions come back unanswered. Which one do you refuse to proceed without?

Walk through an analysis you got wrong and what changed

Easy · postmortem · data quality · self-assessment

Describe an analysis of yours that turned out to be wrong after somebody had already acted on it. You have four minutes. The account must name the defect mechanically, the join, the filter, the window or the identity key, rather than describing it as a communication problem. It must also say who did what because of the wrong number, how the error surfaced, how long it stood, and what control you put in place so that class of error cannot reach a decision again. Do not pick an error nobody acted on.

Approach

Recognise what is being probed: whether you can be specific about your own failure without minimising it or performing contrition. The discriminator is whether the defect has a mechanism the listener could reproduce in their own warehouse.
Choose the case by blast radius rather than by comfort. An error nobody acted on tests nothing, and picking one signals that you are managing the interview instead of answering it.
Structure the account in six beats: the number, the decision it drove, the defect, the detection, the correction, the control. Keep the defect to one reproducible sentence, for example an inner join to fct_subscription_period that dropped accounts with no subscription row and so computed retention over payers only.
State the direction of the bias, not only its existence. A filter or join that removes rows usually moves a metric predictably, and knowing which way shows you diagnosed the mechanism rather than patched the symptom.
Be exact about detection and elapsed time. 'A colleague noticed' and 'the row-count assertion failed before publication' are different answers about the same organisation, and the second one is the one your control is supposed to produce next time.
End on the control, its cost, whether it has fired since, and one thing it does not cover.

Follow-up

What did the control cost, and has it fired since? If it never has, how do you know it works?
How long did the wrong number stand before anyone questioned it, and what does that say about the review path it went through?
What is the equivalent mistake you are most likely to make in this role, given the tables you would be working in?