Interview guides · everis

everis Data Scientist Interview Questions & Guide 2026

Modeling drills for a everis data scientist interview: baselines, regression interpretation, class imbalance, model defense.

The 60-second brief

As a Data Scientist at everis, you sit at the intersection of advanced analytics and business transformation. You are not merely building models in a vacuum; you are solving high-impact problems for clients across diverse industries. Your work directly influences decision-making, optimizes operational processes, and creates data-driven products that define the competitive edge of the organizations everis serves.

The boundary with engineering varies enough to be worth asking about directly. Some seats end at the analysis and the writeup; others carry feature pipelines, scheduling and alerting, which decides whether production data plumbing belongs in your prep at all.

Focus areas

Compute utilisation against a defended availability denominator
Correct late-entered timesheets before trending recent weeks
Separate bookings, recognised revenue and collected cash

Overview

The role is dynamic and requires a balance of technical rigor and business acumen. You will be expected to translate complex, often ambiguous client requirements into structured data solutions. Whether you are working on predictive modeling, statistical analysis, or machine learning pipelines, your goal is to deliver actionable insights that provide tangible value. This is a role for those who enjoy the challenge of applying theoretical concepts to real-world, messy datasets within a fast-paced, collaborative environment.

The everis interview process

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

Initial Screening

Most candidates lose this call inside the first two minutes, during the walkthrough of their own background. The account runs chronologically, sits at the level of tools and titles, and never arrives at a decision anyone could have disagreed with. Anchor on a problem instead of a timeline: what the team could not answer, what you did about it, what happened next. Ninety seconds is enough, and stopping on time leaves room for the half of the call that belongs to you. What you ask about how work gets prioritised signals your level more reliably than the walkthrough does.

What to demonstrate

Whether your background summary has a shape (problem, decision, consequence) or is a chronological list of tools and employers
Whether you can account for gaps, short stints and the reason you are looking, unprompted and without hedging
The substance of the questions you ask back, which an experienced screener reads as a level signal

How to prepare

Time your opening walkthrough against a clock. If it runs past two minutes, compress the earliest role into a single clause and spend the recovered time on the most recent one
Write one honest sentence for every gap or short stint visible on your resume and offer it before being asked about it
Prepare questions about how work arrives and gets prioritised: who writes the request, how often priorities change, and what happens to an analysis after it is delivered

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

Iterative Rounds

Because the format is not fixed, prepare the reasoning rather than the ritual. Nearly every version of this round draws on the same underlying material: a design you can defend, a metric you can define exactly, an analysis whose assumptions you can state out loud. Only the wrapper changes, whether that is a take-home, a live case, a deep dive on past work, or a rough estimate on a whiteboard. Answers rehearsed to fit one shape stall the moment the shape differs. Practise naming the assumption behind a number, then saying how much the conclusion moves if that assumption is wrong.

What to demonstrate

Whether your justification for a method survives the question 'why not the simpler thing', including when the simpler thing would have worked
Precision under pressure: what exactly counts as an active user, a conversion or a success, over what window, with what exclusions
Whether you carry an argument through to a recommendation instead of stopping at a list of tradeoffs

How to prepare

For each project you plan to mention, write the metric definition in one sentence: numerator, denominator, time window, exclusions. Say it out loud once, because vagueness shows up in speech before it shows up on paper.
Rehearse the same project at three lengths: two minutes, ten minutes, and a deep dive on one technical decision. Cutting live is harder than it sounds.
For your headline result, write down what would have had to be true for it to be wrong, and how you ruled that out.

Final Team Interviews

A loop is not scored one interview at a time. The people you meet compare notes afterwards, usually in a meeting you are not in, and the outcome turns on what each of them can say about you when asked. That rewards something other than survival: every room needs one specific thing worth repeating, and none of them can contradict another. The common way to lose is to tell the same project four times with different numbers in it, or to be uniformly fine in a way that leaves nobody with anything to argue for.

What to demonstrate

Whether your account of a project survives being told twice, with the same scale, the same metric definition and the same numbers each time
Whether each interviewer leaves with one concrete claim they could make on your behalf later, rather than an absence of complaints
Whether a question you already answered in an earlier room gets the same answer at the same depth, without visible impatience

How to prepare

Write a one-page fact sheet for your two or three main projects that fixes the numbers you will quote: rows of data, the metric as a single sentence, the effect you measured and how long the work took. Say them aloud from the sheet until they come out identical every time
For each kind of room you expect, decide the one sentence you want that interviewer repeating in a debrief, then check during the mock that you said it outright instead of implying it
Rehearse answering the same project question twice in one sitting, the second time as though you had not just answered it, because the thing that needs fixing is the flatness that creeps into a repeated story

Where candidates lose points

Using calendar hours, or a current rate card, as the denominator

Available hours is not days x 8. It must subtract approved leave and region-specific public holidays, scale by fte_fraction, and prorate for hire_date and termination_date inside the period; skipping this produces cross-region utilisation gaps that are purely holiday-calendar artifacts and a fake dip every time a cohort of new hires starts. Equally, bill and cost rates change over time, so joining today's dim_consultant row to last year's hours restates history. Use the rate snapshotted on the time entry, or join dim_consultant on work_date BETWEEN effective_from AND COALESCE(effective_to, 'infinity').

Trending utilisation or revenue on work_date without accounting for timesheet backfill

Time entries are created days to weeks after the work happens, and the backfill tail often runs two to six weeks. A dashboard keyed on work_date therefore shows the most recent weeks as a decline that reverses on every refresh. The fix is either to hold the reporting window back past the observed backfill tail (measure the tail with the timesheet submission lag metric rather than guessing) or to report an as-of-entered_at snapshot so the series is internally consistent, and to state which one you used.

Dropping rows with missing values without naming the mechanism

Say whether the values are missing at random, missing by a known process, or missing in a way that depends on the outcome, and handle them accordingly. Deleting incomplete rows silently redefines the population whenever missingness correlates with what you are measuring.

Reporting a p-value with no effect size or interval

Give the estimated difference with a confidence interval in the units the business cares about, then say whether that whole interval is worth acting on. A p-value only addresses whether you can rule out exactly zero; it says nothing about magnitude.

Questions & practice

Can you 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.
Sanity-check the answer against a simple bound or a simulated case.

Follow-up

How would you explain this result to someone who does not know statistics?
What sample size would you need to detect an effect half this size?

Explain the difference between supervised and unsupervised learning.

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.
Say what the estimate is of, and over what population it generalises.

Follow-up

How would you explain this result to someone who does not know statistics?
What sample size would you need to detect an effect half this size?

What are the assumptions of a linear regression model?

Medium · machine learning and modelling

Approach

Check what information would not exist at prediction time, and exclude it.
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.

Follow-up

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

Describe how a specific machine learning algorithm functions at a high level.

Medium · machine learning and modelling

Approach

Check what information would not exist at prediction time, and exclude it.
Frame the prediction: the label, the moment of prediction, and the action it triggers.
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?

Cluster bootstrap a margin change across few, unequal accounts

Hard · cluster bootstrap · few clusters · mix shift

engagements has engagement_id, client_id, pricing_model, fees_usd, cost_usd and period in {pre, post} around a rate-card change. There are about 35 client_ids across roughly 400 engagements, and the top five clients carry a large share of fees. Estimate the pre-to-post change in value-weighted gross margin within pricing_model, and give a 95% interval by resampling whole client_ids with replacement, B = 2000. Write the bootstrap yourself; no resampling library. Report the account-weighted estimate alongside and explain any divergence.

Approach

Write the statistic as a pure function of a dataframe first. Within each pricing_model, margin = (sum(fees) - sum(cost)) / sum(fees) per period; the headline is the fee-weighted average of the within-model differences using fixed pre-period weights, so a shift in the mix of work sold cannot masquerade as a change in delivery.
Resample clusters, not rows: draw 35 client_ids with replacement and concatenate all engagements of each drawn client. A client drawn twice contributes its rows twice under distinct pseudo-ids, which is what preserves within-account correlation instead of averaging it away.
Recompute the statistic on each replicate and take a percentile interval from the 2.5th and 97.5th quantiles. With concentrated fees the replicate distribution is skewed, so a symmetric point plus or minus 1.96 times a standard error is wrong in the tail that matters.
Compute the account-weighted version (mean across clients of each client's margin change) next to the value-weighted one, and attribute the divergence to concentration rather than to noise; if they disagree in sign, that fact is the finding.
Name the regime honestly: at roughly 35 clusters both cluster-robust standard errors and the pairs cluster bootstrap under-cover, so state the fix you would run next, which is a wild cluster bootstrap with Rademacher weights or CR2 with t(G-1) critical values.

Worked solution (40 min)

stat(df): pivot fees and cost by (pricing_model, period), compute per-model margins, difference post minus pre, and weight the differences by each model's pre-period fee share; return one scalar.
Pre-split the frame into a dict of client_id to its rows, so each replicate is a concat of 35 preselected blocks rather than a boolean filter over 400 rows.
rng = np.random.default_rng(11); for b in range(2000): draw client ids with replacement, concat their blocks, call stat, store; assert the replicate's nunique cluster draw count is 35 every time.
ci = np.quantile(reps, [0.025, 0.975]); compute the account-weighted estimate as the unweighted mean of per-client margin changes over clients present in both periods.
Re-run a row-level bootstrap on the same data for contrast and record both interval widths, then leave-one-client-out to see whether one account drives the point estimate.

Expected result: A point estimate stated in margin points, a percentile interval from 2000 cluster replicates that is wider than the row-level bootstrap interval on the same data, an account-weighted estimate reported beside it, and an explicit note that at 35 clusters the interval still under-covers.

Verify it yourself

Every replicate draws exactly 35 clusters; replicate row counts vary while cluster counts do not.
The row-level bootstrap interval is narrower than the cluster one; quantify the ratio rather than assert it.
The point estimate lies inside the percentile interval, and the interval is asymmetric around it when fees are concentrated.
The within-model differences plus the mix term reconcile to the naive pooled change, which shows the decomposition is complete.

Follow-up

Implement the wild cluster bootstrap and show at what cluster count its p-value separates from the naive one.
One client is 30% of fees. Show the interval with and without that account and say which one you would present, and to whom.
What pre-period check would make you willing to call this a causal effect of the rate card rather than a correlation?

Engagement margin without fan-out across two fact tables

Medium · fan-out · join grain · mix shift

fct_engagement holds engagement_id, pricing_model and contract_value_usd. fct_invoice_line holds engagement_id, line_type, amount_usd and status. fct_time_entry holds engagement_id, hours, cost_rate_usd, is_billable and status. For engagements closed last year, return fees (line_type IN ('fees','milestone','credit_note') and status <> 'draft'), delivery cost (SUM(hours * cost_rate_usd) over approved entries, billable and non-billable alike) and gross margin, grouped by pricing_model. A single SELECT joining the engagement to both fact tables and then aggregating produces wrong numbers: say what the error is, then write the correct query.

Approach

Do the arithmetic out loud. An engagement with 40 qualifying invoice lines and 900 approved time entries yields 36,000 rows on the double join: SUM(amount_usd) comes back 900 times too large and SUM(hours * cost_rate_usd) 40 times too large. The two inflation factors are different, so the ratio moves too — per engagement the double join replaces the cost-to-fee ratio with (cost / fees) * (line count / entry count), so a true 30 percent margin reads as 1 - 0.7 * (40 / 900), about 97 percent.
Know which shape of this bug actually survives review. The ratio is preserved only where an engagement carries the same number of qualifying invoice lines as approved time entries, and then only as a row-count-weighted margin, 1 - SUM(cost_i * k_i) / SUM(fees_i * k_i), which still differs from the true pooled margin unless k_i is constant across engagements. So you get either a total absurd enough to tempt someone into a scaling patch, or, on a population where the two counts happen to track each other, a believable-looking ratio sitting on fees and cost that are each wrong by orders of magnitude.
Aggregate each fact table to engagement grain in its own CTE, then LEFT JOIN both onto fct_engagement. One row per engagement then holds by construction rather than by inspection.
Include non-billable delivery hours in cost. Rework, unbilled travel and pursuit time on a live account are real fully-loaded cost, and excluding them flatters fixed-fee work specifically, which is the mix you most need to see clearly.
Treat zero and NULL as different: an engagement with no invoice lines has undefined margin, not zero. Divide by NULLIF(fees, 0) and keep those engagements in a labelled bucket instead of letting an inner join hide them.
Group by pricing_model before reporting any firm-wide figure, and publish the fee mix next to it. Fixed-fee margin falls as hours rise, uncapped time-and-materials margin does not, so a shift in what was sold moves the pooled number with no change in delivery at all.

Follow-up

Decompose a period-over-period margin move into a within-pricing-model component and a between-model mix component, and show the two sum to the total.
Where does not_to_exceed_usd change the time-and-materials picture, and how would you find engagements that crossed it?
Roll this up to the account through parent_client_id. What must the recursive CTE guard against?

Find signed engagements with no approved billable hour

Medium · anti-join · null semantics · not exists

fct_engagement holds engagement_id, start_date and status. fct_time_entry holds time_entry_id, consultant_id, engagement_id, charge_code, work_date, hours, is_billable and status, and engagement_id is NULL on bench, leave, training and internal rows. Return engagements with start_date in the trailing quarter and status IN ('active','closed_delivered','closed_early') that have no approved billable time entry with work_date within 45 days of start_date, giving engagement_id, start_date and days elapsed. Then explain why NOT IN over a subquery selecting fct_time_entry.engagement_id is the wrong instrument here.

Approach

Express the exclusion as NOT EXISTS with a correlated predicate covering all four conditions at once: te.engagement_id = e.engagement_id AND te.is_billable AND te.status = 'approved' AND te.work_date < e.start_date + INTERVAL '45 days'. NOT IN can only carry a single column, so a multi-condition anti-join forces a contorted subquery even before the NULL problem.
State the NULL semantics precisely: NOT IN (SELECT engagement_id FROM fct_time_entry) evaluates to NULL rather than TRUE for every candidate as soon as one NULL is present in the list, because x <> NULL is unknown. The WHERE clause keeps only TRUE, so the query returns zero rows and reads as a clean bill of health. This table guarantees NULLs, since bench and leave rows carry no engagement.
Note the equivalent LEFT JOIN ... WHERE te.engagement_id IS NULL form. It is correct, but it materialises a join only to discard most of it; NOT EXISTS states the intent and most planners execute both as the same anti-join.
Guard the window against truncation: an engagement that started 10 days ago cannot yet have failed a 45-day test, so require start_date <= current_date - 45 or report the too-early set separately rather than counting them as failures.
Decide on the late-timesheet risk explicitly. A missing entry may mean unstaffed work or an unsubmitted timesheet, so either hold the cutoff back past the measured submission lag or label the recent tail as provisional.

Worked solution (20 min)

Count engagements matching the status and start_date predicates; this is the denominator.
Write the NOT EXISTS version and record its row count.
Write the NOT IN version on the same data and observe zero rows, then confirm with SELECT COUNT(*) FROM fct_time_entry WHERE engagement_id IS NULL that NULLs are present.
Cross-check by counting engagements that DO have a qualifying entry and verifying the two counts sum to the denominator.
Open one engagement from the result and look at its raw time entries to see whether the cause is no staffing or unapproved timesheets.

Expected result: A short list of engagement_id, start_date and days_since_start for engagements that started at least 45 days ago and carry no approved billable hour in their first 45 days. The NOT IN variant returns zero rows on the same data.

Verify it yourself

Count of flagged engagements plus count of engagements with at least one qualifying entry equals the count of engagements matching the status and date filters.
Every returned engagement has start_date at or before current_date - 45.
Spot-checking one flagged engagement in fct_time_entry shows either no rows or only unapproved or non-billable rows.
Replacing NOT EXISTS with LEFT JOIN ... IS NULL returns an identical set.

Follow-up

Turn this into a time-to-first-billable-hour distribution. What do you do with engagements that never recorded one?
Should client_pursuit hours count as the engagement being staffed, and how does that choice change the list?
How would you prove the empty result from the NOT IN version is a bug rather than good news?

Describe how you would prioritize features for a new data product.

Medium · product sense and metrics

Approach

Name one primary metric, then the guardrail that stops it being gamed.
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

Which segment would you cut first, and what would that rule out?
What would you do if the primary metric and the guardrail moved in opposite directions?

If a project isn't delivering the expected results, how do you pivot your strategy?

Medium

Approach

Work from the decision backwards to the evidence you would need.
Say what you would check first and why it is the highest-information step.
Clarify what is being asked and what a complete answer would contain.

Follow-up

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

Estimate a mandatory pricing review at a value threshold

Hard · regression discontinuity · manipulation test · fuzzy rd · local estimand

Proposals with expected_value_usd at or above 250,000 must pass a mandatory pricing review before submission; below that the originating partner prices unilaterally. The rule has stood for three years, nothing was randomised, and leadership wants to know whether the review improves realisation on the resulting engagements. About 900 proposals a year land in fct_proposal, and realisation is only observable for those that reach stage = won. Design the identification strategy, state the estimand precisely, and name the two checks that would make you abandon the design.

Approach

Set up the design. Running variable is expected_value_usd as recorded when the rule is applied, cutoff 250,000, outcome realisation on the resulting engagement. Estimate with local linear regression either side, triangular kernel, MSE-optimal bandwidth and robust bias-corrected confidence intervals. Do not fit a global high-order polynomial, which drags weight from proposals far from the cutoff onto the estimate at it.
Check compliance before calling it sharp. If some sub-threshold proposals are reviewed voluntarily or some above-threshold ones skip review, the design is fuzzy, which is instrumental variables with the threshold indicator as the instrument. The estimate is a Wald ratio, the jump in realisation divided by the jump in review probability, and it identifies the effect for compliers at the cutoff only.
Run the manipulation test and interpret it carefully. A density test on expected_value_usd will very likely reject, because proposal values heap at round numbers and 250,000 is exactly such a number. Heaping alone is not sorting, but a partner pricing at 249,000 to dodge review is, and both look the same in the density. Separate them by checking whether excess mass appears only just below the cutoff or at round numbers throughout the range, and by running a donut specification that drops a window around the threshold.
Check covariate continuity at the cutoff for industry_segment, account_tier, is_competitive, practice_area and originating_partner_id, using the same local linear specification with each covariate as the outcome. A jump in any of them at 250,000 is a jump in the population rather than in the treatment, and it kills the design.
Confront the outcome-side selection. Realisation exists only for won proposals, and review may itself move the win rate, so conditioning on a win conditions on a post-treatment variable. Estimate the RD on win rate first; if it jumps, switch to an outcome defined over all proposals, such as realised fees per proposal with losses entering as zero, or report Lee bounds rather than a point estimate.
Size the design before committing to it. Only proposals inside the bandwidth contribute, so 2,700 proposals over three years with a bandwidth capturing perhaps 15% leaves an effective sample near 400 split across the cutoff. Compute the MDE on that number, not on 2,700, and say in advance whether it can detect the effect that would change the policy.

Worked solution (45 min)

Histogram expected_value_usd in fine bins around 250,000 and across the full range, to separate generic round-number heaping from cutoff-specific sorting.
Estimate the first stage: probability of a recorded review as a function of the running variable, and read the jump at the cutoff. A jump well below one means fuzzy, so move to the Wald ratio.
Run the local linear RD on realisation with an MSE-optimal bandwidth and robust bias-corrected intervals, then repeat at half and twice that bandwidth.
Repeat the same specification with each pre-treatment covariate as the outcome, and with placebo cutoffs at 200,000 and 300,000.
Run the RD on win rate, then on realised fees per proposal defined over all proposals, and compare the three results.
Report the MDE computed on the in-bandwidth proposal count alongside the estimate.

Expected result: A fuzzy RD estimate reported as a Wald ratio with robust bias-corrected intervals, described explicitly as the effect for compliers at a 250,000 proposal value, accompanied by covariate-continuity and placebo-cutoff checks that do not jump, and an MDE computed on the in-bandwidth sample rather than on three years of proposals.

Verify it yourself

Point estimates at half and twice the MSE-optimal bandwidth should sit inside the main estimate's confidence interval; strong bandwidth sensitivity means the fit is picking up curvature rather than a jump.
Placebo cutoffs away from 250,000 should show no discontinuity; one that does means the specification is finding structure that is not the rule.
The first-stage jump must be large enough to keep the Wald ratio stable; a jump below roughly 0.2 in review probability makes the denominator small and the instrument weak.
The donut estimate and the full-sample estimate should agree; a large gap points at sorting just below the threshold rather than at a treatment effect.

Follow-up

If the density test rejects and the donut specification moves the estimate materially, what do you conclude and what do you put in the deck?
The estimand is local to 250,000 and leadership wants to know whether to lower the threshold to 100,000. What can you honestly say?
The review is triggered on the value at submission, but the value is revised afterwards. Which version of the running variable do you use, and why?

Two-year-old engagement margins moved after a dimension join change

Hard · type-2 scd · restatement · effective dating

After a warehouse release, gross margin on engagements closed two years ago changed by up to six points, upward on some and downward on others. The cost model now joins dim_consultant on consultant_id AND is_current = TRUE to read standard_cost_rate_usd, instead of using the cost_rate_usd already snapshotted on each fct_time_entry row. Available columns include consultant_sk, consultant_id, level, standard_cost_rate_usd, effective_from, effective_to, is_current, termination_date. Explain the restatement, quantify who it favours, and specify the join you would ship.

Approach

State the mechanism in one line: joining a type-2 dimension on is_current pastes today's cost rate onto historical hours, so every consultant promoted or re-rated since restates their own history in the direction their rate moved. Because promotions differ per person, engagement margins move in both directions, which is exactly the observed pattern.
Quantify with three parallel cost computations per engagement: (a) the snapshotted fct_time_entry.cost_rate_usd, (b) an effective-dated join using work_date BETWEEN effective_from AND COALESCE(effective_to, 'infinity'), and (c) the shipped is_current join. Report the distribution of (c) minus (a) and correlate it with the share of hours delivered by staff who have since been promoted.
Check cardinality as a separate defect: an is_current join can drop consultants whose current row is missing or whose termination retired the row, and can fan out if consultant_id carries more than one current row. Compare hour totals before and after the join; they must be identical.
Decide the canonical source and justify it: the snapshotted rate on the time entry is what was booked and is authoritative for financial restatement. The effective-dated join is the reconciliation, and a systematic disagreement between (a) and (b) is its own defect worth raising rather than papering over.
Reissue the affected periods with an explicit changeover note, and pin the rule in a test that fails if is_current appears in any join from a fact table to a type-2 dimension on a historical grain.

Follow-up

Some entries have cost_rate_usd NULL or zero. Which source wins then, and what does that do to your reconciliation?
The same pattern exists for bill_rate_usd. What does it do to realisation, and in which direction?
How would you sweep every model in the warehouse for this class of bug without reading each one?

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.

Explaining a method to someone who will not follow the maths

Half of this section is about translation. Be ready to describe how you explained a result to someone who did not want the method, only the implication, and what you did when the simplified version started being repeated in a way that overstated it. Correcting your own simplification is a strong beat.

Describe a situation where you had to work under tight deadlines.

Medium · behavioural and stakeholder questions

Approach

Pick a story where you drove the decision, not one where you observed it.
Name the disagreement or constraint, and how you resolved it with evidence.
State the situation in two sentences and spend the rest on your reasoning.

Follow-up

What would you do differently if you ran that project again?
What did you decide not to do, and why?

Walk me through a time you had to explain a complex technical result to a non-technical stakeholder.

Medium · behavioural and stakeholder questions

Approach

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

Follow-up

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

Answering a request to redefine the utilisation denominator

Hard · denominator integrity · restatement · escalation

Before a quarterly review, a practice lead asks for two changes to reported billable utilisation: drop consultants allocated to engagements with status = 'paused' out of the denominator, and count approved travel hours booked to client_delivery as billable. Together the changes move reported utilisation from 71 to 79 percent. You must answer in writing today. Give your answer, the principle you apply to each change separately, and what you do if you are overruled.

Approach

Name the probe: whether you can hold a measurement line by adjudicating each proposal on its merits, rather than treating the request as bad faith or accepting it to avoid a fight.
Adjudicate the paused-engagement change against what the denominator means. Billable utilisation measures the share of available consultant hours that were sold. A consultant whose engagement is paused is still available and still costs salary, which is precisely the situation the metric exists to reveal. Removing them defines away the signal, so this one is refused on definitional grounds, not on suspicion.
Adjudicate the travel change as an empirical question, because it is one. If those hours are billed to the client, is_billable and bill_rate_usd should already reflect it; if they are charged and then written off or never invoiced, counting them raises utilisation while realisation falls. Check the invoice lines for the same engagement and period rather than arguing about principle.
Quantify each change separately, and the interaction. An eight-point move made of one point and seven points is a different conversation from two four-point moves, and the lead cannot make a good decision without that split.
If a change is accepted, restate history on the new definition and publish the old series alongside it with the date of the change. A definition applied forward only makes every period-over-period comparison meaningless. If overruled, comply with the restatement and the footnote, and escalate only the part that is a misstatement of fact rather than a defensible choice.

Follow-up

Which of the two changes would you accept, and what evidence flips your answer on the other one?
The lead wants the new definition applied only from this quarter forward. Why is that worse than applying it to history, and how do you explain that in one sentence?