Interview guides · State Street

State Street Data Scientist Interview Questions & Guide 2026

Practice explaining analysis before a State Street data scientist interview: the recommendation, the uncertainty, the follow-ups.

The 60-second brief

As a Data Scientist at State Street, you operate at the intersection of traditional financial services, massive global scale, and cutting-edge artificial intelligence. You are responsible for designing, developing, and deploying advanced data models, machine learning architectures, and generative AI solutions that directly impact global investment servicing, asset management, and corporate audit functions. Your work empowers institutional clients, streamlines internal operations, and safeguards the financial investments of millions of people worldwide.

When randomisation is off the table, the skill being checked is naming an identification strategy together with the assumption it rests on: parallel trends for difference-in-differences, relevance and exclusion for an instrument, overlap and conditional ignorability for matching. Say the assumption out loud and say how you would try to break it.

Focus areas

Measure churn only on renewal-eligible accounts
Analyse at the account grain, cluster errors
Read NRR on a fixed account cohort

Overview

This position bridges complex financial mathematics with modern software engineering and data infrastructure. You might build retrieval-augmented generation pipelines for institutional research, develop agentic workflows to automate data governance, or engineer predictive models that optimize global custody services. The problems you solve are technically intricate and require balancing innovation with the rigorous risk management frameworks expected of a premier global financial institution.

Expect a high-visibility environment where your models translate raw structured and unstructured data into strategic business intelligence. You will collaborate closely with software engineers, product managers, and financial analysts to bring production-grade AI solutions to life. Success in this role demands technical mastery, sharp product intuition, and the ability to articulate complex quantitative findings to non-technical stakeholders.

The State Street interview process

State Street candidates report 2 rounds · ≈ 2-4 weeks. The stages below are what candidates describe, not a published process.

Recruiter Screening

Data Scientist covers at least four different jobs: experimentation, product analytics, causal work on observational data, and applied modelling that ships into a system. A screening call is the cheapest place to find out which of them is being hired for, and doing that diagnosis openly reads as senior rather than fussy. Ask what the last few pieces of work on the team actually were, and roughly how a week splits between querying, modelling and stakeholder time. Then say which parts of that you have done and which you have not. Claiming the whole range is the fastest way to be caught one round later.

What to demonstrate

Whether you can distinguish the flavours of the role and locate your own experience inside one of them honestly
Whether you name what you have not done instead of stretching to cover every line of the posting
Whether your hard constraints (notice period, location, work authorisation, level) surface now rather than at offer stage

How to prepare

Map the last two years of your time into rough percentages across query writing, experiment design, modelling and stakeholder work, so a question about scope has a real answer
Mark every responsibility in the posting as done, adjacent or new, and prepare one sentence for each adjacent item naming the closest thing you have actually built
Decide which logistics are non-negotiable before the call so you can state them in one sentence rather than negotiating live

Technical Assessments

Much of what gets scored here happens out loud while you type. Nobody can see your reasoning inside a half-written query, so five silent minutes read as being stuck even when they are not. State the plan in plain language first: which tables, what grain you are aggregating to, and the one filter that defines the population. Then write it. The narration doubles as insurance, because a wrong plan gets caught early and cheaply while a wrong query gets caught at the end with no time left to redo it. A timed statistics section, where one exists, is a separate test with its own clock.

What to demonstrate

Whether the query you write matches the plan you just described
What you do with a hint, meaning whether the correction gets absorbed or the first approach gets defended
Whether you can debug your own wrong output by reading the result set and naming which part of the query produced the anomaly

How to prepare

Solve three problems while screen-sharing into a recording, then watch it back and mark every stretch longer than thirty seconds where you said nothing
Practise compressing the plan into one sentence before typing, then check afterwards whether the finished query actually matched it
Time yourself on statistics questions that carry a business reading, such as what a confidence interval does and does not claim, rather than re-reading notes without a clock

Where candidates lose points

Comparing accounts that received a sales or customer-success touch against those that did not

Assignment of coverage is deliberate and pulls in both directions at once: the largest accounts get a named owner because they are valuable, and the accounts showing distress get one because they are at risk. The comparison therefore mixes a strong positive selection with a strong negative one, and the naive estimate can come out with either sign depending on which assignment rule dominated during the period examined. Nothing about matching on observed size fixes this, because the risk signal that triggered coverage is usually the same signal that predicts the outcome. It needs either an actual randomised or staggered rollout of coverage, or a design built on a capacity constraint or territory boundary that assigns coverage for reasons unrelated to account health.

Treating raw request or usage volume as engagement

Most traffic in this domain is emitted by machines. Continuous-integration pipelines, scheduled batch jobs, synthetic monitors, backfills and client retries can all grow by an order of magnitude from one configuration change made by one engineer, and none of it represents a new decision to use the product. The inversion is what makes it dangerous: when the platform degrades, clients retry, so error-driven retry volume rises at the exact moment the customer is most likely to leave, and an engagement dashboard built on raw counts shows growth immediately before a churn. Filter on traffic_class and on successful status before anything else, and keep failed-request volume as its own separate series.

Over-explaining the method and under-explaining the implication

Lead with the answer and what you would do about it, then give the approach when asked. Roughly one sentence of method per three of implication is the right ratio for a stakeholder-facing answer; the interviewer already knows what a regression is.

Comparing periods without accounting for seasonality or day-of-week

Compare whole weeks against whole weeks and check whether the same swing appeared in prior cycles or prior years before attributing it to anything you changed. Weekday and weekend populations often differ enough that a Tuesday-to-Saturday comparison is meaningless.

Questions & practice

Focuses on core statistical concepts, hypothesis testing, and probability distributions relevant to financial modeling.

Medium · statistics and probability

Approach

Translate the result into the decision it informs, in one plain sentence.
Write down the assumption the method needs before you use the method.
Sanity-check the answer against a simple bound or a simulated case.

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 design an A/B test for a new algorithmic recommendation feature on an investment dashboard?

Medium · machine learning and modelling

Approach

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.
Frame the prediction: the label, the moment of prediction, and the action it triggers.

Follow-up

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

Permutation-test a consumption experiment randomised at account level

Hard · permutation-test · heavy-tails · cuped · experiment-readout

An experiment randomised 900 accounts into two arms. You have one row per account: account_id, arm, consumption_28d (billable units after launch) and consumption_pre (the 28 days before). Consumption is heavy-tailed and the largest account is several percent of the total. Write a permutation test from scratch: winsorise at the pooled 99th percentile as a pre-registered rule, use the difference in arm means of the winsorised outcome as the statistic, and obtain a two-sided p-value from 20,000 relabellings of the account-level arm vector. Report the observed effect, the p-value, and the same test on a CUPED-adjusted outcome.

Approach

Be precise about what the permutation test needs. Under the sharp null of no effect for any account, the outcomes are exchangeable across arm labels, and the test is valid for ANY statistic T(outcomes, labels) provided the identical function is applied to the observed labels and to all 20,000 relabellings. The pooled 99th percentile is a function of the outcome vector alone, so recomputing it inside the loop returns the same number 20,000 times: that is wasted CPU, not a bias, and hoisting it out is an optimisation rather than a correctness fix. Say plainly that capping at all changes the estimand from mean consumption to mean capped consumption; it is not a neutral cleaning step.
The mistake that does invalidate the test is an asymmetry between the observed statistic and the permuted ones, and the easiest way to create it is to derive the cleaning rule from the observed arm labels and then freeze it — winsorise each arm at its own observed 99th percentile, hold those two caps fixed, and permute. The observed value is then computed with caps matched to its own partition while every relabelling is scored with caps belonging to a different one, so the null distribution no longer answers the question the p-value claims to answer. A per-arm cap recomputed consistently inside every permutation is a valid test, but it estimates a contrast whose two sides are capped at different thresholds, so prefer the pooled cap on estimand grounds and pre-register it.
Permute the account-level arm vector, because the account is the randomisation unit. Relabelling anything finer — users, workspaces, requests — generates a null distribution narrower than the design actually supports and returns p-values that are anti-conservative.
Vectorise the null: tile the treatment indicator into a (B, n) matrix and permute along axis 1 with rng.permuted(..., out=...). The statistic is a difference of means, so the treated sum alone determines it and the whole null is one matrix-vector product. Use the two-sided p-value (1 + count(|stat_perm| >= |stat_obs|)) / (B + 1); the plus-one on each side is not cosmetic, it keeps the p-value away from exactly zero and keeps the test valid at finite B.
For CUPED, fit theta = cov(y, x) / var(x) on the pooled data and use that same theta for the observed statistic and every relabelling. Pooled theta, like the pooled cap, carries no label information, so where in the loop you compute it is again only a performance question; fitting theta within arms is what goes wrong, because the adjusted outcome then depends on the labels and an observed-label fit frozen across all 20,000 relabellings breaks the match between observed and permuted statistics. x must be measured entirely before launch, which consumption_pre is. Expected variance reduction is about 1 - corr(y, x)^2; measure the achieved reduction from the two null distributions rather than asserting it.

Worked solution (45 min)

cap_y = np.quantile(df.consumption_28d, 0.99); y = np.minimum(df.consumption_28d.to_numpy(float), cap_y); cap_x = np.quantile(df.consumption_pre, 0.99); x = np.minimum(df.consumption_pre.to_numpy(float), cap_x)
t = (df.arm == 'treatment').to_numpy(); n1 = int(t.sum()); n0 = len(t) - n1; obs = y[t].mean() - y[~t].mean()
rng = np.random.default_rng(11); L = np.tile(t.astype(np.int8), (20_000, 1)); rng.permuted(L, axis=1, out=L); s1 = L @ y; stats = s1/n1 - (y.sum() - s1)/n0
p = (1 + int(np.sum(np.abs(stats) >= abs(obs)))) / (20_000 + 1)
theta = np.cov(y, x, ddof=1)[0,1] / np.var(x, ddof=1); y_adj = y - theta*(x - x.mean()); repeat steps 2 to 4 on y_adj and compare stats.std(ddof=1) between the two runs.

Expected result: A two-sided p-value strictly between 1/20001 and 1, an observed effect expressed in capped billable units per account, and a CUPED null whose standard deviation is smaller than the unadjusted one by roughly sqrt(1 - corr(y, x)^2). The CUPED point estimate stays close to the unadjusted one, since the adjustment removes variance rather than shifting the effect.

Verify it yourself

The permutation null is centred near zero: |mean(stats)| is a small fraction of std(stats).
An A/A run, relabelling arm at random before the test and repeating over seeds, gives roughly uniform p-values with about 5% below 0.05.
std(stats_cuped) < std(stats) whenever corr(y, x) is materially non-zero, and the ratio matches sqrt(1 - r^2) to within simulation noise.
Moving the pooled cap computation inside the permutation loop reproduces the same p-value bit for bit at the same seed — the direct demonstration that a pooled cap carries no label information — while setting the cap to infinity reproduces the uncapped test exactly, so the winsorisation switch is independently verifiable.

Follow-up

The p-value is 0.04 with the cap and 0.31 without it. What do you report, and what did you pre-register?
Colleagues in a shared workspace can see the treated behaviour. How does that change the design and the estimate?
How many accounts would you need to detect a 5% lift given this outcome's distribution?

Given a table of client trades, write a query to rank trades by volume within each asset class using dense ranking functions.

Medium · sql and data manipulation

Approach

Compute rates by summing numerator and denominator separately, never by averaging rates.
Handle the rows that do not match: a LEFT JOIN with a NULL check is usually the question.
Check whether any join is one-to-many before aggregating, or the sums inflate.

Follow-up

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

Evaluates your proficiency in querying complex, large-scale databases and handling relational data transformations efficiently.

Medium · sql and data manipulation

Approach

Compute rates by summing numerator and denominator separately, never by averaging rates.
Handle the rows that do not match: a LEFT JOIN with a NULL check is usually the question.
Check whether any join is one-to-many before aggregating, or the sums inflate.

Follow-up

How does the query change if the join becomes one-to-many?
How would you verify this result without re-running the same query?

Consecutive qualifying weeks before renewal, as a ranked worklist

Hard · gaps and islands · window functions · date boundaries

fct_api_request carries account_id, workspace_id, environment, request_at (timestamptz), http_status and traffic_class. fct_subscription_period carries account_id, term_end_date, auto_renew and is_current. A qualifying week for an account is an ISO week with at least 50 successful production requests in traffic_class ('interactive','batch'). Over the last 52 whole ISO weeks, and for accounts whose current term ends within 90 days, return the current qualifying-week streak length, the week it began, and the longest earlier streak. An account whose streak has broken must appear with a current length of zero.

Approach

Bucket weeks as date_trunc('week', request_at AT TIME ZONE 'UTC'). request_at is a timestamptz, so an unpinned date_trunc silently uses the session time zone, weeks start at a local midnight, and Monday-morning traffic lands in the previous week for part of the fleet. Pinning UTC also makes the seven-day arithmetic below exact across daylight-saving transitions.
Apply the exclusions before counting: environment = 'production', http_status < 400, traffic_class IN ('interactive','batch'). Then apply the volume floor and drop the current partial week, which can never meet a floor calibrated on whole weeks.
Build islands with the row-number anchor: ROW_NUMBER() OVER (PARTITION BY account_id ORDER BY week_start) as rn, then week_start - rn * interval '7 days' is constant inside a run of consecutive weeks. Group by that anchor to get each streak's start, end and length.
The current streak is the island whose end equals the last whole week; if none does, the account's current streak is zero and that is the interesting case. The longest earlier streak is the maximum length among the remaining islands.
Join the renewal filter from the current subscription row and LEFT JOIN the streak summary so an account with no qualifying week at all still appears, rather than vanishing from the risk list precisely because it went quiet.
Finish with an operating point. The list is worked by a team with finite capacity, so order it and cut it at that capacity, and say what happens to the accounts below the line.

Worked solution (40 min)

Build weekly_qualified: filter the fact on environment, status and traffic_class, group by account_id and date_trunc('week', request_at AT TIME ZONE 'UTC'), keep groups with count(*) >= 50, and exclude the in-progress week and anything older than 52 whole weeks.
Add rn = ROW_NUMBER() OVER (PARTITION BY account_id ORDER BY week_start) and anchor = week_start - rn * interval '7 days'.
Group by (account_id, anchor) to get streak_start = min(week_start), streak_end = max(week_start), streak_len = count(*).
Per account, take current_len as the streak_len where streak_end = the last whole week else 0, current_start from the same island, and longest_prior as max(streak_len) over the other islands.
Join to fct_subscription_period on is_current with term_end_date <= current_date + 90, LEFT JOIN the streak summary, and order by current_len ascending then term_end_date ascending.

Expected result: One row per renewal-eligible account with current_streak_weeks, current_streak_start_week and longest_prior_streak_weeks, where an account with no qualifying week in the last whole week returns current_streak_weeks = 0 and still appears, ordered so the quietest imminent renewals sit at the top.

Verify it yourself

Per account, the sum of all island lengths equals the count of qualifying weeks for that account.
current_streak_weeks > 0 if and only if the last whole week is a qualifying week for that account.
No island contains a gap: re-deriving consecutive differences inside an island returns exactly 7 days everywhere.
An account qualifying in all 52 weeks returns a single island of length 52 and a null-free current streak start.

Follow-up

The floor of 50 requests was picked for this exercise. How would you calibrate it from data, and what would force a recalibration?
A regional holiday week drops several accounts below the floor at once. How do you keep that out of the risk list?
How would you evaluate whether contacting these accounts actually changed renewal, given that coverage is assigned deliberately?

How would you design product metrics for an internal AI-driven document intelligence tool used by analysts?

Medium · product sense and metrics

Approach

Restate the decision this analysis has to support, and who acts on the answer.
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

How would you detect that the metric is being gamed rather than genuinely improving?
Which segment would you cut first, and what would that rule out?

How would you measure the success and productivity gains of adopting generative AI code-generation tools across engineering teams?

Medium · product sense and metrics

Approach

Fix the population and the time window before naming any metric.
Restate the decision this analysis has to support, and who acts on the answer.
State what result would change your recommendation, so the answer is falsifiable.

Follow-up

How would you detect that the metric is being gamed rather than genuinely improving?
Which segment would you cut first, and what would that rule out?

A key engagement metric for our investment management platform dropped by fifteen percent week-over-week. How would you investigate this drop?

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.
State what result would change your recommendation, so the answer is falsifiable.

Follow-up

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

How do you prioritize competing requests from multiple business units when your team has limited modeling bandwidth?

Medium · product sense and metrics

Approach

Decompose the metric into the rates that drive it, and say which one you would check first.
Fix the population and the time window before naming any metric.
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?

How do you determine sample size and statistical significance when running experiments with low-frequency institutional trades?

Medium · a/b testing and experimentation

Approach

State the primary metric and the minimum effect worth shipping, then size the test.
Name the guardrails that would stop a launch even on a positive primary result.
Name the randomisation unit first; it decides the variance and what the test can detect.

Follow-up

What would you do if you could not randomise at all?
What would you conclude if the result is positive but the test is underpowered?

What are some common experimentation pitfalls, such as sample ratio mismatch or network effects, and how do you mitigate them?

Medium · a/b testing and experimentation

Approach

Decide the analysis before seeing data, including how long it runs and when you look.
Name the randomisation unit first; it decides the variance and what the test can detect.
State the primary metric and the minimum effect worth shipping, then size the test.

Follow-up

How would you handle interference between treated and control units?
What would you do if you could not randomise at all?

Cut variance with pre-period usage before the test starts

Medium · cuped · variance-reduction · stratification

You are planning an account-randomised test on 2,800 paying accounts. The outcome is a 28-day sum of billable_quantity for sku_code = 'compute_hours' from fct_usage_daily, and the same account's 28-day pre-period sum correlates 0.80 with it. 420 accounts were created inside the pre-period and have partial or no history. Specify the variance-reduction plan: the adjusted estimator and where its coefficient comes from, how assignment is stratified, how the 420 incomplete accounts are handled, and what must change in the pre-period window given that fct_usage_daily rows are restated after first write.

Approach

Write the estimator explicitly: Y_adj = Y - theta * (X - mean(X)), with theta = Cov(X, Y) / Var(X). Estimate theta from pre-experiment history or pooled across arms, never separately by arm and never from post-treatment outcomes. Fitting theta on treatment-arm outcomes folds the effect being measured into the adjustment and biases the result toward whatever the treatment did.
Quantify the gain and convert it into the currency the team cares about. The residual variance multiplier is 1 - 0.80^2 = 0.36, so the standard error falls to 0.60 of its unadjusted value and the MDE falls with it. That is the same precision as running with 1 / 0.36, about 2.8 times as many accounts, which matters because the account population is fixed and cannot be bought with a longer run.
Stratify assignment on pre-period usage decile crossed with the three paid plan tiers, giving 30 cells at roughly 93 accounts each, and collapse any cell below about 20. Use the same strata in the analysis through strata fixed effects or post-stratification: stratified assignment analysed pooled discards much of the gain, and stratified analysis without stratified assignment risks empty cells in the top decile, which is precisely where the revenue sits.
Handle the 420 incomplete accounts by imputing X at the stratum mean and adding a binary indicator for missing pre-period, rather than dropping them. Dropping silently redefines the population to established accounts, which is usually the opposite of the segment a new feature targets, and it makes the result non-generalisable in a way the readout will not disclose.
Fix the window against restatement. Measure the empirical settling time by comparing a usage_date's total at first_written_at against its value after restated_at has stopped moving, then end the pre-period that many days before assignment. A pre-period whose last days are still settling carries recency-correlated measurement error in the covariate, which both weakens rho and can correlate with assignment date.
Pre-register the whole plan before assignment: the estimation set for theta, the strata definition and collapsing rule, the imputation rule, the winsorisation cap and the trailing exclusion. Every one of these can be tuned after the fact to move a p-value, which is why they are worth nothing if decided afterwards.

Worked solution (30 min)

Estimate rho on a historical pair of adjacent 28-day windows, applying exactly the traffic-class and is_internal filters the live experiment will use.
Compute the variance multiplier 1 - 0.80^2 = 0.36 and translate it to a standard-error multiplier of 0.60 and an effective-sample multiplier of about 2.8.
Build 30 strata from ten pre-period usage deciles crossed with three paid plan tiers, inspect the minimum cell count and collapse cells below about 20 accounts.
Measure the metering settling time from first_written_at against restated_at and shift the pre-period window back by that many days.
Write the pre-registration: theta source, strata, imputation for the 420 incomplete accounts, winsorisation cap, trailing exclusion.

Expected result: Standard-error multiplier 0.60 and effective-sample multiplier about 2.8 at rho = 0.80, with 30 strata collapsed where thin, the 420 incomplete accounts retained through stratum-mean imputation plus a missingness indicator, and the pre-period ending one measured settling window before assignment.

Verify it yourself

Adjusted and unadjusted point estimates must be close under valid randomisation, because this reduces variance rather than moving the estimate. A large shift means theta was fitted on post-treatment data or that randomisation itself failed.
The multiplier 1 - rho^2 is monotone in the absolute correlation and equals 1 at rho = 0, so at rho = 0.30 the standard error can only fall by about 5%. Any larger claimed reduction at that correlation is arithmetically wrong.
Computing the pre-period sum twice, a week apart, should return the same number once the settling window is excluded. If it does not, the exclusion window is too short.

Follow-up

Once continuous-integration and synthetic traffic are excluded, rho turns out to be 0.45 rather than 0.80. What is the revised variance reduction, and is the added complexity still worth it?
How would you extend this to more than one covariate, and what stops you from adding twenty?
Does this adjustment repair an imbalance you discover after assignment, or only reduce variance? Be precise about the difference.

Monthly logo churn triples with no change in satisfaction

Hard · renewal-eligible base · censoring · timestamp semantics

Monthly logo churn, computed as churned accounts divided by all paying accounts, tripled last month. Contracts are annual. From fct_subscription_period (account_id, term_start_date, term_end_date, amendment_type, auto_renew, booked_at, superseded_by_id, is_current) and dim_account (account_id, churned_at, account_status, employee_band, acquisition_channel), rebuild churn on the renewal-eligible base, separate calendar effects from customer behaviour, and state whether retention actually changed. Note that churned_at is sometimes set when the record was updated rather than at term end.

Approach

Rebuild the denominator as accounts whose term_end_date falls in the month. An account eleven months from renewal sits in the current denominator while being structurally incapable of entering the numerator, so on annual contracts the published rate understates the truth by roughly the reciprocal of the annual renewal fraction and moves with the signing calendar.
Plot the renewal-eligible base by month across two years. A signing surge twelve months earlier reproduces itself as an eligibility surge now, and a rate whose denominator ignores that tracks the sales calendar rather than customer sentiment.
Date each churn by term_end_date, never by churned_at or an update timestamp. Inspect the distribution of churned_at minus term_end_date: a backlog cleared in one batch appears as a mass at a single date and shifts losses into whichever month the operations team did its paperwork.
Apply the 45-day grace for late renewal paperwork so the most recent month and a half is marked not reportable, rather than printing a number that will rise once the paperwork lands.
Compare corrected gross logo retention against its own trailing distribution, and if a real change survives, cut it by employee_band, acquisition_channel and plan_tier before proposing any cause.

Follow-up

Some contracts in the window have not reached their renewal date. When does this require a survival estimator rather than a simple rate, and which one would you use?
How do you report churn to an audience that wants a monthly number when the underlying event is annual and lumpy?

Suggested practice checklist

Four days spend equal time on query work, statistics, modelling and product judgement at deliberately shallow depth, which produces a scored map of where you actually stand. The last three days spend everything on the two areas the role weights most, and close by re-running day one to measure movement.

Day 1 — Breadth pass: query fluency

Solve six prompts spanning aggregation, joins, window functions and date arithmetic in 60 minutes total, stopping at 10 minutes each whether or not it works, and mark every prompt as solved, solved slowly, or stuck.
For each unsolved prompt write the single blocking sentence (I lost the grain, I did not know the frame clause, I could not express the date boundary) instead of reading the solution.
Translate one pandas transformation you know well into SQL and one SQL query into pandas, checking that both return the same row count and the same totals.

Deliverable: A scored six-row table, one line per prompt, saved for the day-seven re-run.

Day 2 — Breadth pass: statistics and inference

Answer ten short questions in writing with nothing open: what a p-value is conditional on, what a 95 percent interval covers across repeated samples, when a paired test is the right one, what the bootstrap estimates, why multiple comparisons inflate false positives, how controlling the family-wise error rate differs from controlling the false discovery rate, what power depends on, what a missed real effect costs a product, the three situations where the central limit theorem does not rescue you (small n, very heavy tails, dependent observations), and what a standard error is the standard deviation of.
Grade yourself against a reference and count only the answers that were exactly right, not the ones that were nearly right.
Rewrite the two weakest answers the following morning from memory in full sentences.

Deliverable: Ten graded answers with an honest count of exact hits.

Day 3 — Breadth pass: modelling

Take one tabular dataset end to end in 90 minutes: a leakage-safe split, a baseline that is not a model (majority class or historical mean), one regularized linear model, one gradient-boosted tree, and a single evaluation metric chosen before you look at any result.
Write why that metric fits the cost structure: precision at a fixed recall for alerting, calibration for anything feeding a price or a threshold, ranking metrics for retrieval, and note that area under the ROC curve is insensitive to class balance in a way that can flatter a rare-positive problem.
Name the leak you were most likely to introduce (an encoding fit on all rows before splitting, or a feature computed after the label's timestamp) and write the check that would have caught it.

Deliverable: A notebook whose first cell states the metric and the baseline, plus two lines on what beat what and by how much.

Day 4 — Breadth pass: product judgement

Answer three case prompts aloud at 15 minutes each, timing how long passes before you state a success metric.
For one case write the first segmentation you would run and the row counts you expect per segment, so that a tiny segment cannot quietly drive the conclusion.
Take a metric definition you did not write, from a public dashboard, a textbook, or documentation you already have open, and list every place two analysts implementing it would diverge: which rows the denominator admits, whether the unit is an account or a person, what the time window is anchored to, and what happens to data that arrives late. Then write the one question that would close the largest of those gaps.

Deliverable: Three recorded case answers plus an ambiguity list for a metric someone else defined, ending in the single question you would ask about it.

Day 5 — Depth, first area

Rank the four areas by how many bullet points in the role description each one covers, pick the top one, and spend the entire day inside it.
Work the six hardest problems you can find in that area and for each write the generalizable move you should have reached for first, rather than the answer.
Re-solve the two you failed the same evening with notes closed.

Deliverable: Six generalizable moves written as instructions to yourself, not as solutions.

Day 6 — Depth, second area, and the seam between them

Repeat the depth protocol on the second-ranked area with the same six-problem structure.
Construct one problem that requires both areas at once, for example a metric redefinition whose effect you must validate with a test whose readout you then have to query.
Solve your own combined problem end to end and note where the handoff between the two areas cost you time.

Deliverable: One combined problem, solved end to end, with the handoff failure written down.

Day 7 — Integration and re-measurement

Re-run the six prompts from day one under the same clock and compare both correctness and time.
Run a 60-minute mixed mock that moves between areas without warning, since switching cost is what breadth passes do not train.
Write the two areas you would still fail on, and the sentence you will use in the interview when you hit one of them.

Deliverable: A before-and-after score table plus a written plan for the two remaining gaps.

Where your data came from

Data people depend on systems owned by other teams, and much of the job is negotiating for instrumentation, access, or a fix to a broken pipeline. Prepare an example of getting something changed upstream that you did not control. Describe what you asked for, what you traded, and how you worked while you waited.

How do you handle multi-collinearity when building predictive regression models for financial risk?

Medium · behavioural and stakeholder questions

Approach

Close with what you would do differently, concretely.
State the situation in two sentences and spend the rest on your reasoning.
Name the disagreement or constraint, and how you resolved it with evidence.

Follow-up

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

Allocate one analyst week across three competing requests

Easy · prioritisation · stakeholders · scoping

Three requests arrive the same morning and you have one week. Finance wants per-account gross margin from fct_usage_daily for a pricing review in three weeks. Sales wants a renewal-risk list for accounts with term_end_date inside 60 days. A product manager wants an experiment readout for a decision being taken on Thursday. Produce your allocation with hours attached, what you say to whoever receives less, and one thing you refuse to do this week, with the reason each decision is defensible to the person it costs.

Approach

The interviewer is probing whether you prioritise on decision timing and reversibility or on who asked most forcefully. Sort by the date each decision is actually taken and by what the default outcome is if nothing arrives.
Apply that sort concretely. The Thursday readout has a hard irreversible deadline and no value afterwards. The pricing review has three weeks of slack. The renewal list has a rolling deadline set by term_end_date, so part of it is urgent this week and the rest is not, which means it can be split rather than deferred whole.
Find the cheapest sufficient version of each request rather than the full version. The readout goes in full. The renewal list ships as a filtered query over renewal-eligible accounts ranked by two inspectable signals rather than as a model. The margin work is scoped to the accounts that dominate the pricing decision, since revenue is heavily skewed and the tail will not change the conclusion.
Make the trade visible in one written note to all three at once, with dates. Telling each person separately that they are the priority is how an allocation becomes a credibility problem.
Refuse something explicitly and say why. The model version of the renewal list is the usual candidate, because it cannot be evaluated without a holdout nobody has agreed to yet, and building it this week forecloses that.
Leave slack. A plan with none is a plan to miss the one deadline that cannot move.

Follow-up

The sales leader escalates to your manager. What did you already do that makes that a short conversation?
Which of the three deadlines would you push back on, and what exactly would you ask for?
What would you change about how these requests reach you so next week is not the same?

Disagree with a product manager about an adoption claim

Medium · conflict · telemetry hygiene · adoption metrics

A product manager is about to present that a new SDK release drove a 40 percent rise in requests among adopting accounts, computed from fct_api_request counts grouped by sdk_version. You find the rise is concentrated in traffic_class equal to ci, that rows with is_retry true grew alongside it, and that restricting to interactive non-retry traffic leaves a 3 percent lift. The launch review is in two days. Decide how you raise this, with whom and in what order, and what you propose the claim becomes.

Approach

The interviewer is probing whether you can correct a colleague without ambushing them, and whether your own counter-analysis carries the caveats theirs lacked. Go to the product manager privately before the review. A correction delivered in the room is a status move and loses the argument you are actually trying to win.
Bring a decomposition rather than a verdict: the same accounts and window, requests split by traffic_class with retries held out as their own column, so their 40 percent and your 3 percent reconcile line by line and neither has to be taken on trust.
Reproduce their figure exactly first. If you cannot land on 40 percent with their method, you do not yet know what you are disagreeing with.
Ask whether the continuous-integration lift is itself valuable. An account wiring the SDK into its pipeline has increased integration depth, which is the dominant switching cost in this domain, so the honest claim may be that integration depth rose while interactive usage moved 3 percent. Improving the claim beats deleting it.
Name the mechanism that makes the raw count dangerous: clients retry when the platform degrades, so retry volume climbs exactly when the customer is most at risk. Pull the 5xx rate for the same accounts and window before anyone concludes anything, and note that billable_units is zero on 5xx rows, so request counts and billable quantities diverging is itself the signal.
Close with a standing definition for launch metrics so the next release does not repeat the exercise.

Follow-up

The product manager argues that continuous-integration traffic is real usage and declines to split it out. Is that position defensible, and under what metric definition?
Suppose the 5xx rate for those same accounts also rose 40 percent. What is the claim now?
The review happens and the raw number is presented regardless. What do you do next, and what do you not do?