Airtel Digital Data Scientist Interview Questions & Guide 2026

The 60-second brief

As a Data Scientist at Airtel Digital, you are at the intersection of massive-scale telecommunications data and high-velocity product innovation. This role is pivotal in transforming billions of daily user touchpoints into actionable insights that drive product strategy, optimize network resource allocation, and enhance the digital experience for millions of subscribers. You aren't just building models; you are solving complex, real-world problems that directly impact the bottom line of one of the world's largest digital ecosystems.

Seniority shifts the scope more than the words in the title do. Earlier-career loops mostly check that you execute a well-posed analysis correctly; senior loops check that you can decide which question is worth answering and defend what you chose not to do.

Focus areas

• Read NRR on a fixed account cohort
• Separate contracted seats from actively used seats
• Analyse at the account grain, cluster errors

Overview

The work environment is fast-paced and data-intensive, requiring a blend of rigorous statistical thinking and product-centric pragmatism. You will collaborate with cross-functional teams—including product managers, engineers, and business leaders—to design metrics that define success and develop predictive solutions for everything from churn prevention to infrastructure optimization. This role is ideal for individuals who enjoy translating ambiguous business challenges into structured, testable hypotheses and thrive in an environment where technical depth is matched by business impact.

The Airtel Digital interview process

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

Coding 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

Machine Learning Rounds

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.

Manager/HR Discussion

Rounds outside the standard loop often open with something deliberately under-specified: a loose business problem, an open question about a product area, a dataset described in one sentence. The common failure is surveying, listing six plausible approaches and committing to none of them. The thing that separates a strong answer is scoping out loud. State what you are treating as the goal, name the metric you would move, say what you are choosing not to do and why, then take one path through to an actual answer. An interviewer can follow you down a narrow path. Nobody can grade a menu.

What to demonstrate

• Whether you turn an ambiguous prompt into a stated question with a measurable outcome before doing any work
• The judgement visible in what you cut, and whether you say why you cut it rather than silently dropping it
• Whether you land on a concrete recommendation with its caveat attached, rather than an unranked set of options

How to prepare

• Take three vague prompts, such as 'is this feature working', 'why did retention drop', and 'should we expand into a new segment'. For each, write one sentence of goal, one primary metric with its window, and two things you are explicitly not doing.
• Practise giving the recommendation first and the reasoning second, in five minutes. Loosely defined rounds are usually time-boxed, and an answer that arrives last often does not arrive.
• Keep a running assumption list as you talk, on paper or in the shared doc, so the interviewer can challenge one assumption instead of your whole answer.

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.

Computing monthly churn against the entire customer base when contracts are annual

An annual contract has no opportunity to churn except at its renewal date, so an account that is eleven months from renewal is in the denominator while being incapable of appearing in the numerator. The resulting rate is smaller than the real one by roughly the ratio of the base to the renewal-eligible base, and it oscillates with the seasonality of when deals were originally signed rather than with anything about the customers. The corresponding trap on the other side is counting a churn on the date the record was updated rather than on term_end_date, which shifts losses into whichever month the operations team did its paperwork.

Averaging per-user rates to produce a population rate

Decide which quantity you want: the mean of per-user ratios and the ratio of summed numerator to summed denominator are different estimands, and heavy users dominate one but not the other. For a ratio metric, aggregate numerator and denominator separately and use the delta method for its variance.

Analysing at a different unit than the one randomised

Say out loud what was randomised (user, device, account, cluster) and make the analysis unit match, or account for the clustering with cluster-robust standard errors, the delta method, or aggregation up to the randomised unit. Randomising users and then running a test over sessions understates variance and inflates the false-positive rate.

Questions & practice

Explain the concept of p-values and their role in hypothesis testing.

Medium · statistics and probability

Approach

1. Translate the result into the decision it informs, in one plain sentence.
2. Quantify uncertainty explicitly rather than reporting a point estimate alone.
3. Say what the estimate is of, and over what population it generalises.

Follow-up

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

How would you handle missing values or outliers in a large dataset before feeding it into a model?

Medium · machine learning and modelling

Approach

1. Say how the offline result would be validated online before it is trusted.
2. Check what information would not exist at prediction time, and exclude it.
3. Pick an evaluation metric that matches the cost of each error type, not a default.

Follow-up

• How would you choose the decision threshold, and who owns that choice?
• What would you monitor after launch to know the model is still valid?

Simulate how the renewal calendar distorts monthly churn rates

Medium · simulation · churn · numpy · cohorts

Simulate 1,200 accounts on annual contracts. Draw each account's renewal month from a deliberately lumpy calendar: 30% renew in January and the remaining 70% are spread evenly over the other eleven months. At each renewal an account churns with probability 0.18, independent of month; survivors renew and come back twelve months later. Run 24 simulated months. For each month compute two rates: churned accounts over all live accounts, and churned accounts over accounts whose term ended that month. Report the mean and the month-to-month standard deviation of each series, and state which one belongs in an executive summary.

Approach

1. Build the panel with numpy state arrays rather than a per-account loop: a next_renewal_month vector, an alive boolean vector, and a loop over the 24 months only. Looping over 24 months is fine; looping over 1,200 accounts inside it is what makes the simulation too slow to iterate on.
2. Maintain the live set honestly. An account that churned in month m must leave the denominator from m+1 onward and can never be renewal-eligible again; if it stays, the naive rate drifts downward for reasons that have nothing to do with churn and the calendar effect gets buried.
3. Compute both series over the same months and compare dispersion, not only level. The eligible-base rate should sit near 0.18 with binomial noise scaled by that month's renewal count; the naive rate spikes in January and collapses in thin months.
4. Quantify the gap instead of describing it: the ratio of the two means is roughly the reciprocal of the average monthly renewal-eligible fraction, and the naive series' standard deviation is driven by the signing calendar rather than by customer behaviour.
5. Check against the closed form before trusting the output. With the live set maintained correctly the eligible-base rate is an unbiased estimator of 0.18 in every month, so a systematic offset means the bookkeeping is wrong, not that the simulation found something.

Worked solution (30 min)

1. rng = np.random.default_rng(0); p = [0.30] + [0.70/11]*11; next_renewal = rng.choice(12, size=1200, p=p); alive = np.ones(1200, bool)
2. For m in range(24): eligible = alive & (next_renewal == m); churn = eligible & (rng.random(1200) < 0.18); record churn.sum(), eligible.sum(), alive.sum() at month start; alive &= ~churn; next_renewal[eligible & ~churn] += 12
3. naive = churned / live_at_start; eligible_rate = churned / eligible, left as NaN where eligible == 0.
4. Report naive.mean(), naive.std(ddof=1), np.nanmean(eligible_rate), np.nanstd(eligible_rate, ddof=1) and the ratio of the two means.

Expected result: The eligible-base rate averages close to 0.18 (roughly 0.17 to 0.19 at this sample size) with no January spike. The naive rate averages near 0.015, about one twelfth of it, and its January values run several times a typical month, so its month-to-month standard deviation is a large fraction of its own mean.

Verify it yourself

• The 24 monthly churn counts sum to 1200 minus the final alive count.
• Switching the calendar to uniform (p = 1/12 everywhere) collapses the naive series' dispersion while leaving the eligible-base mean unchanged.
• Setting the churn probability to 0 makes both series identically zero and leaves 1,200 accounts alive.
• Quadrupling the account count roughly halves the standard deviation of the eligible-base rate without moving its mean.

Follow-up

• Compounded over twelve months the naive rate lands close to the true annual churn. Does that rescue it?
• How would you report churn in a month where only nine accounts were renewal-eligible?
• Eighteen-month terms are now being sold alongside annual ones. What breaks?

How do you use SQL window functions to calculate rolling averages or identify trends in customer usage data?

Medium · sql and data manipulation

Approach

1. Say which table is the grain you start from, and join outward from it.
2. Check whether any join is one-to-many before aggregating, or the sums inflate.
3. Compute rates by summing numerator and denominator separately, never by averaging rates.

Follow-up

• How would you verify this result without re-running the same query?
• What breaks if events arrive late or out of order?

Given a table of user activity, write a query to identify the top 3 most active users per region.

Medium · sql and data manipulation

Approach

1. Say which table is the grain you start from, and join outward from it.
2. Check whether any join is one-to-many before aggregating, or the sums inflate.
3. Compute rates by summing numerator and denominator separately, never by averaging rates.

Follow-up

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

Seven-day activation rate by signup cohort week

Easy · funnel · cohorts · censoring

dim_account carries account_id, created_at, is_internal and is_current; fct_api_request carries account_id, request_at, http_status, api_key_id and traffic_class. Build a signup cohort by the ISO week of created_at over accounts with is_internal = false. An account counts as activated when it issues a request with http_status < 400, a non-null api_key_id and traffic_class <> 'synthetic_monitor' within 168 hours of its own created_at. Return cohort accounts, activated accounts and the rate per week, and exclude any week that has not yet fully elapsed its 168-hour window.

Approach

1. Collapse dim_account to one row per account_id before anything else. It is a type 2 dimension, so a plan or status change gives the same account several rows; filtering to is_current = true is the cheapest correct choice here because created_at does not change across versions.
2. Express the window as interval arithmetic on the timestamptz column: request_at >= created_at AND request_at < created_at + interval '168 hours'. A date-difference of 7 days is a different and wrong condition for accounts created mid-day.
3. Test activation with EXISTS rather than a join to MIN(request_at). EXISTS short-circuits, keeps the cohort at one row per account, and cannot fan out.
4. Aggregate by date_trunc('week', created_at AT TIME ZONE 'UTC'), counting accounts and activated accounts, and divide as a ratio of counts.
5. Drop unreportable weeks: the last account in a cohort week is created just under week_start + 7 days, so the week is only complete once now() >= week_start + interval '14 days'. Without that filter the newest week always looks like a regression.

Worked solution (20 min)

1. Write the cohort CTE: SELECT account_id, created_at FROM dim_account WHERE is_current AND NOT is_internal AND created_at >= <window start>.
2. Add the activation predicate as a correlated EXISTS over fct_api_request on account_id with the four conditions: http_status < 400, api_key_id IS NOT NULL, traffic_class <> 'synthetic_monitor', and the 168-hour bracket.
3. Group by date_trunc('week', created_at AT TIME ZONE 'UTC'); select count() AS cohort_accounts, count() FILTER (WHERE activated) AS activated_accounts, and the ratio cast to numeric.
4. Add HAVING or an outer WHERE that keeps only weeks where week_start + interval '14 days' <= now().
5. Spot-check one account that activated on hour 167 and one that activated on hour 169 to confirm the boundary is exclusive at the top.

Expected result: One row per ISO cohort week with cohort_accounts, activated_accounts and activation_rate between 0 and 1; the newest row is at least 14 days old, and accounts with no rows at all in fct_api_request appear in the denominator with activated = 0 rather than disappearing.

Verify it yourself

• Summing cohort_accounts across weeks equals the count of non-internal current-version accounts created in the same window.
• Re-running the query a day later leaves every previously reported week byte-identical; any movement means the censoring filter is wrong.
• activated_accounts is never greater than cohort_accounts, and the count of distinct account_id in the activated set matches a separate COUNT DISTINCT over the fact table.

Follow-up

• The median time-to-first-successful-call is more informative than a fixed-window rate. Why can you not compute it from this query, and what estimator does it need?
• How would you separate accounts that never called from accounts that called and got only 4xx responses, and which of those is a product problem?

We are launching a new feature in the Airtel app; how would you design the product metric to measure its success?

Medium · product sense and metrics

Approach

1. Restate the decision this analysis has to support, and who acts on the answer.
2. Fix the population and the time window before naming any metric.
3. 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?
• Which segment would you cut first, and what would that rule out?

How would you determine if an increase in a specific metric is due to a seasonal trend or a successful product intervention?

Medium · product sense and metrics

Approach

1. Decompose the metric into the rates that drive it, and say which one you would check first.
2. Fix the population and the time window before naming any metric.
3. Restate the decision this analysis has to support, and who acts on the answer.

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?

If we observe a sudden drop in a key engagement metric, how would you approach a metric drop diagnosis to identify the root cause?

Medium · product sense and metrics

Approach

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

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 decide on the sample size required for an A/B test to ensure your results are reliable?

Medium · a/b testing and experimentation

Approach

1. Name the guardrails that would stop a launch even on a positive primary result.
2. Decide the analysis before seeing data, including how long it runs and when you look.
3. 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?
• How would you handle interference between treated and control units?

What are the common experimentation pitfalls you must watch out for when running tests on a large user base?

Medium · a/b testing and experimentation

Approach

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

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?

Design the retention metric suite for a quarterly board pack

Hard · net revenue retention · cohort arithmetic · as-of joins · gaming resistance

You own the retention numbers in the quarterly board pack. Build them from fct_subscription_period (account_id, arr_cents, term_start_date, term_end_date, amendment_type, booked_at, is_current, superseded_by_id) rather than from invoices. Deliver net revenue retention over a trailing twelve months, the guardrails that stop it being satisfied by shrinking the business, and the reporting lag you will enforce. Specify the cohort rule, state whether you report a ratio of sums or a mean of per-account ratios and why, and name two ways the headline number rises while the business gets worse.

Approach

1. Freeze the cohort at month M-12: the set of accounts with ARR above zero on that date. No account acquired after M-12 enters either side of the ratio. That constraint is the entire point, because it makes the number a statement about the installed base rather than about how well sales did last quarter.
2. Read arr_cents from the fct_subscription_period version that was live on each of the two dates, selected by term_start_date and term_end_date bracketing the date, never by is_current, which silently rates last year's revenue at this year's plan. Invoiced amounts move with billing_frequency and prepayment and will not reconcile to a contract-derived figure, so pick one source and say which.
3. Report the ratio of sums: total arr_cents at M over the frozen cohort divided by total at M-12. The mean of per-account ratios is a different estimand and much noisier on a few thousand accounts, because contraction is bounded below at zero while expansion is unbounded, so a handful of large expansions dominate the mean.
4. Attach the two guardrails that close the two gaming routes. Gross logo retention on the renewal-eligible base catches raising the ratio by declining to serve the churn-prone segment, because it is computed only over accounts that actually had an opportunity to leave. New-logo ARR reported beside it exposes a contracting top of funnel that the ratio is structurally incapable of seeing.
5. Enforce the lag and the restatement policy. A 45-day grace on term_end_date for late paperwork means the most recent 45 days are never reportable, and a month is openly restated when the grace closes rather than quietly corrected between board packs.

Worked solution (40 min)

1. Build an as-of ARR resolver: for a date D and an account, select the fct_subscription_period row where term_start_date <= D and term_end_date >= D, breaking ties on the latest booked_at so a superseded version never wins.
2. Form the cohort at M-12 as accounts with as-of ARR above zero, then compute both sums with that account set held fixed.
3. Compute the same quantity as a mean of per-account ratios and record the gap between the two.
4. Build gross logo retention over accounts with term_end_date in each month, with the 45-day grace applied, and pull new-logo ARR from amendment_type = 'new' by booked_at.
5. Recompute net revenue retention with the five largest accounts removed and report it beside the headline.

Expected result: Net revenue retention as a ratio of sums on a cohort frozen at M-12, reported beside gross logo retention on the renewal-eligible base and new-logo ARR, with the most recent 45 days marked not reportable. The answer names at least two ways the headline rises while the business worsens: ceasing to sell into the churn-prone segment, and expansion concentrated in a few accounts masking broad contraction underneath.

Verify it yourself

• The cohort account count must be identical at M and at M-12; a larger count at M means accounts acquired inside the window leaked into the numerator.
• A churned account must contribute zero to the numerator and its full M-12 ARR to the denominator, not be dropped from both, which would silently raise the ratio.
• Net revenue retention recomputed without the five largest accounts must be reported; a headline that moves by more than a few points under that removal is a statement about those accounts rather than about the base.
• Summed as-of ARR must not exceed the sum over is_current rows by more than the amendment rate; a large excess means the as-of join is returning several contract versions per account.

Follow-up

• Compute net revenue retention both ways on the same cohort. What does a large gap between the ratio of sums and the mean of per-account ratios tell you about the shape of the expansion distribution?
• A ramp deal is signed in March and starts in July. Which month does it belong to on the board's sales-effectiveness page, and which on this one?

Weekly active organisations fell nine percent over one week

Easy · seasonality · denominators · segmentation

A dashboard reports the weekly active organisation ratio on a trailing seven-day window ending each Wednesday. This week it reads nine percent below last week. You have fct_api_request (account_id, environment, traffic_class, http_status, request_at) and dim_account (account_id, billing_country, account_status, is_internal, is_current). Nothing was released. Decide whether usage actually fell, and hand back a corrected series plus a one-paragraph explanation that a non-analyst can repeat without you in the room.

Approach

1. Count the holiday-free business days inside each window before comparing them. A trailing seven-day window spans exactly five weekdays wherever it ends, so its business-day count can only fall to four or fewer when a public holiday lands inside it and can never reach six, while usage in this domain follows a hard five-to-two weekday cycle. Two windows holding different numbers of business days are not comparable whatever the product did.
2. Count distinct active accounts per calendar day for the last ten weeks and overlay the two windows. A calendar problem shows as a small number of weekdays sitting at weekend level, not as every day being uniformly lower.
3. Cut the daily series by billing_country and index each country-day to that country's trailing same-weekday median, which isolates a regional public holiday from a product change.
4. Check the denominator on its own: the metric divides by accounts whose account_status was in trial, free or active_paid for the whole week, so a batch suspension or status backfill moves the ratio with no change in the numerator at all.
5. Report the series with each window's business-day count and the holiday dates annotated beside it, and state the residual week-over-week change that survives once the calendar effect is removed. Compare against earlier windows holding the same number of business days rather than dividing by business days, since distinct-account counts are sublinear in window length and dividing would over-correct.

Follow-up

• Distinct account counts are sublinear in the number of days in the window. Why does losing one of five business days reduce the count by noticeably less than twenty percent?
• How would you make this metric comparable across countries with different holiday calendars without hand-maintaining a holiday table forever?

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.

Describe the most difficult situation you have faced in a professional setting and how you resolved it.

Medium · behavioural and stakeholder questions

Approach

1. Quantify the outcome, including what you would not claim credit for.
2. State the situation in two sentences and spend the rest on your reasoning.
3. Pick a story where you drove the decision, not one where you observed it.

Follow-up

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

Scope an open-ended request to predict account churn

Medium · scoping · churn modelling · operating point

A customer success director asks for a list of accounts about to churn. You know only that the team has six people and that contracts are annual. Available data is fct_subscription_period, fct_usage_daily, fct_api_request, fct_support_ticket and dim_account. Before writing any code, produce the questions you need answered, a proposed definition of about to churn, and the shape of the artefact you would hand back, including the operating point that turns a score into a decision.

Approach

1. The interviewer is probing whether you convert a vague request into a decision with a capacity constraint attached. A candidate who starts talking about model families has already failed the exercise.
2. Pin the event and the horizon first. Churn is only possible at term_end_date, so the population is accounts renewing in the next 60 to 90 days, not the whole base. Ask explicitly whether contraction and downgrade count as churn or only full non-renewal, because the three have different base rates and different interventions.
3. Pin the action and the capacity. Six people times a realistic number of meaningful interventions per week gives k, and k is what the list is ranked to. Evaluate on precision at k rather than a global AUC over accounts that will never be contacted.
4. Audit leakage before choosing features. Every feature needs a timestamp proving it existed before the prediction date. A downgrade amendment, a churn reason code, and a ticket opened after the renewal conversation started are all leaks that will make the offline number look excellent and the live list useless.
5. Ask for the counterfactual now rather than later. Coverage is assigned deliberately, so without a held-out slice agreed at the start the intervention can never be evaluated, and you will be asked for its impact in nine months regardless.
6. Propose the smallest artefact that closes the loop: a weekly ranked list sized to capacity with two or three inspectable reasons per row, plus a stated policy for accounts below the line.

Follow-up

• The director insists all accounts are in scope, not only those renewing soon. How do you answer without simply refusing?
• Historical non-renewals number about 30 a year. At what point do you tell them a model is the wrong tool and a rules list is better?
• Which candidate features would you drop purely because you cannot date them?

Report an underpowered consumption test to a non-technical executive

Medium · communication · uncertainty · experimentation

An account-randomised packaging change ran six weeks across 900 paying accounts. The effect on billable units per account per month is plus 4.1 percent, with a 95 percent interval from minus 3.2 to plus 11.8 after clustering standard errors at the account and applying the pre-registered winsorisation at the 99th percentile. An executive with no statistical background wants one number this week to decide a full rollout. Produce a three-sentence spoken answer, one chart, and an explicit recommendation of ship, stop or keep running, with the cost of each option stated.

Approach

1. The interviewer is probing whether you can be decision-useful without either hiding the uncertainty or hiding behind it. Start from the decision rather than the statistics: establish what the executive would do differently at plus 4 percent versus zero, because if the action is identical the interval does not matter.
2. Translate the interval into consequences in units the executive already reasons about. Multiply both endpoints by the cohort's baseline consumption and contracted rates to give an annualised revenue range, so the answer is a range of dollars rather than a range of percentages.
3. Price the option to wait. Using the observed variance, state roughly how many additional account-weeks halve the interval width, so keep running becomes a quantified choice instead of a stall.
4. Offer a cheaper path to the same decision: a lower-variance proximate outcome such as successful billable units on the new SKU, or CUPED using each account's pre-period consumption, quoting the expected variance reduction as one minus the squared pre-post correlation.
5. Give a recommendation and name the single observation that would reverse it. A strong answer commits; a generic one recites the interval and leaves the decision on the table.

Follow-up

• The executive says it clearly works and is just not provable, so ship it. What is your answer?
• How much of the interval width comes from clustering and how much from the revenue tail, and what would you do about each?
• If you had to ship this week with no more data, which guardrail would you watch for the first fortnight and at what threshold would you roll back?