Altimetrik Data Scientist Interview Questions & Guide 2026

The 60-second brief

As a Data Scientist at Altimetrik, you occupy a pivotal position at the intersection of advanced analytics and high-impact business solutions. You are not merely building models; you are solving complex, real-world problems for global clients, often involving large-scale data environments similar to those found in fintech and enterprise digital transformation. Your work directly influences product strategy, operational efficiency, and customer experience.

How much statistics you need depends on the flavour of the seat. Experiment-facing work wants you deep enough to notice that repeated looks at accumulating data inflate the false positive rate of a fixed-sample test; modelling-facing work wants estimation and honest uncertainty intervals.

Focus areas

• Separate authorization, settlement and dispute outcomes cleanly
• Read vintage curves, not blended portfolio averages
• Decompose expected loss into PD, LGD, EAD

Overview

The role demands a balance of rigorous academic knowledge—such as statistical theory—and the practical ability to deploy scalable solutions. You will navigate the full data lifecycle, from initial feature engineering and model selection to the deployment of production-ready pipelines. At Altimetrik, you are expected to be a consultant as much as a scientist, translating technical complexity into actionable business value.

The role is highly collaborative. You will frequently work alongside cross-functional teams and, in some instances, directly support major client accounts, requiring both technical depth and professional maturity.

Where to focus your preparation

Treat the sections below as preparation areas and confirm the format with your recruiter.

Preparation focus

No round sequence has been reported for this company, so work the categories below and confirm the format with your recruiter.

What to demonstrate

• Breadth across SQL, experimentation and product reasoning
• Ability to state assumptions before choosing a method

How to prepare

• Drill the practice exercises below and time yourself
• Prepare three quantified stories about decisions you drove

Where candidates lose points

Recalibrating an underwriting cutoff on approved and funded applicants only

Rejected applicants have no repayment outcome, and they were rejected because the incumbent model scored them badly, so the missingness depends directly on the outcome being modelled. Reject inference by augmentation or parcelling fills the gap using the incumbent model's own assumptions, which means it can confirm those assumptions but cannot test them. The only genuinely new information about the reject region comes from bureau performance on rejects who borrowed elsewhere, or from a deliberately randomised approval band around the cutoff.

Counting authorizations instead of weighting them, and summing amounts across currencies

Declines skew toward high-value, cross-border and card-not-present transactions, so an unweighted approval rate can sit flat while approved value falls. Merchant retry logic also turns one declined purchase into several rows, inflating the denominator by an amount that varies by merchant and by decline reason. Amounts are held in the minor unit of the transaction currency and that unit is not always two decimals, since some currencies have none and some have three, so summing amount_minor across currencies produces a figure with no interpretation at all.

Ignoring interference between units in a marketplace experiment

Ask whether one unit's treatment can change another unit's outcome through shared inventory, a matching pool, a social graph or a common budget. Where it can, randomise at a level that contains the spillover, such as region or time slice, and say explicitly what that costs you in statistical power.

Stopping an experiment the moment it crosses significance

Fix the sample size or duration before launch, or use a method built for continuous monitoring such as a sequential test, always-valid confidence intervals, or group-sequential boundaries. Repeatedly checking a fixed-horizon p-value against 0.05 pushes the real false-positive rate well above 5 percent.

Questions & practice

Explain the difference between bias and variance.

Medium · statistics and probability

Approach

1. Say what the estimate is of, and over what population it generalises.
2. Translate the result into the decision it informs, in one plain sentence.
3. Write down the assumption the method needs before you use the method.

Follow-up

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

Describe the importance of p-values and confidence intervals in feature selection.

Medium · statistics and probability

Approach

1. Quantify uncertainty explicitly rather than reporting a point estimate alone.
2. Write down the assumption the method needs before you use the method.
3. 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?

What is the fundamental difference between bagging and boosting algorithms?

Medium · machine learning and modelling

Approach

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

Follow-up

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

How do you assess the statistical significance of a model's performance?

Medium · machine learning and modelling

Approach

1. Pick an evaluation metric that matches the cost of each error type, not a default.
2. Check what information would not exist at prediction time, and exclude it.
3. 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?
• How would you choose the decision threshold, and who owns that choice?

How do you handle overfitting in a linear regression 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. Frame the prediction: the label, the moment of prediction, and the action it triggers.

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?

Implement accident-quarter loss ratio at twelve months development

Medium · loss ratio · development age · earned premium

fct_policy_period_monthly arrives as a stack of month-end snapshots: each row carries valuation_month alongside as_of_month, policy_id, product_line, written_premium_minor, earned_premium_minor, paid_loss_minor, case_reserve_minor, ibnr_reserve_minor and loss_adjustment_expense_minor. Compute the accident-quarter loss ratio at exactly 12 months of development: incurred losses over earned premium, both taken from rows whose as_of_month falls in the accident quarter, read from the snapshot 12 months after that quarter closes. Report quarters that cannot reach that age as incomplete rather than dropping them.

Approach

1. Derive accident_quarter from as_of_month, then define the evaluation snapshot per quarter as valuation_month equal to the quarter's final month plus twelve months. Every figure in the ratio comes from that one snapshot, not from whichever snapshot happens to be newest.
2. Numerator is paid_loss_minor plus case_reserve_minor plus ibnr_reserve_minor over the accident quarter's rows in that snapshot. Loss adjustment expense may be included or not, but the choice applies to every quarter and is named in an output column.
3. Denominator is earned_premium_minor over the same rows. Written premium is booked in full at inception, so in a growing book it runs ahead of earned premium and drags the ratio down, with the error reversing when the book shrinks.
4. Left-join the full quarter list against available valuation months so a quarter with no 12-month snapshot yields status incomplete and a null ratio, instead of disappearing and shortening the series without saying so.
5. Split by product_line, since both the loss ratio level and the speed of development differ by line, and a blended series moves with mix as much as with experience.

Worked solution (30 min)

1. Add accident_quarter and a target_valuation column equal to the quarter end plus twelve months.
2. Filter rows to those where valuation_month equals the row's target_valuation, then assert each accident_quarter has exactly one distinct valuation_month left.
3. Aggregate incurred and earned premium by accident_quarter and product_line and take the ratio.
4. Reindex against the full list of accident quarters and product lines, marking rows with no matching snapshot as incomplete with a null ratio.
5. Recompute one quarter by hand on a five-policy subset and confirm it matches.

Expected result: One row per accident_quarter and product_line with incurred, earned_premium, loss_ratio, an lae_included flag and status in complete or incomplete. Complete quarters end twelve months before the latest valuation_month, so the four or five most recent quarters carry null ratios.

Verify it yourself

• Assert exactly one distinct valuation_month per accident quarter after filtering; more than one means the snapshot join fanned out.
• For a growing book, earned premium in a quarter is below written premium booked in that quarter; if it is above, either the book is shrinking or the accident-quarter derivation is wrong.
• Incomplete quarters carry null ratios and never appear on the same line as complete ones in any chart.
• Swapping the denominator to written premium shifts a quarter by L(W - E)/(EW), so the sign of the change is the sign of written minus earned premium in that quarter: the ratio falls where the book grew and rises where it shrank. Verify the swap per quarter against sign(W - E) rather than expecting a uniform move; a series that moves in one direction everywhere only means the book grew in every quarter.

Follow-up

• The most recent complete quarter came in four points better than the one before. What do you check before calling it an improvement?
• How would you estimate the 12-month figure for a quarter that is only 6 months developed, and how would you label the estimate?
• Why can an expense ratio legitimately use a different denominator from the loss ratio in the same presentation?

Attribute chargebacks to transaction month without fanning out

Medium · fan-out · cohort attribution · maturity

Report the matured first-chargeback rate. Numerator: fct_card_dispute rows whose dispute_stage is first_chargeback, representment, pre_arbitration or arbitration, attributed to the requested_at month of the linked fct_payment_authorization row rather than to opened_at. Denominator: settled authorizations in that same transaction month, meaning settled_at is not null and is_reversal is false. One authorization can carry more than one dispute case. Report only transaction months whose last day is at least 120 days old, and mark the remainder incomplete rather than showing them as low.

Approach

1. Compute the denominator from fct_payment_authorization alone, grouped by the requested_at month, before any dispute table is mentioned, so the join cannot touch it.
2. Compute the numerator as a separate aggregate: join disputes to their authorization only to recover requested_at, then count dispute rows per transaction month with the stage filter.
3. Join the two aggregates on the month key, which keeps the grain at one row per month and makes double counting structurally impossible rather than something you have to remember.
4. Apply the maturity gate on the month's last day plus 120 days against the current date, because a transaction on the final day of the month is the least mature one in the cohort.
5. Emit an explicit status column of 'final' or 'incomplete' instead of filtering immature months away silently, so a reader cannot mistake absence for zero.

Follow-up

• Should the numerator count dispute cases or disputed authorizations? Which one reconciles to the loss line, and which one to the operations queue?
• Some reason codes allow filing well beyond 120 days. How would you estimate the tail on a month you have decided to call final?
• How would you present the incomplete months so that a weekly reader does not read the right-hand slope as an improvement?

Customers with no credit application, avoiding the NOT IN trap

Medium · null semantics · anti-join · scd type 2

Count current customers who have never submitted a credit application, broken out by segment. dim_customer is a slowly changing dimension type 2, so restrict to is_current = true, kyc_status = 'verified' and closed_at null. In fct_loan_application, customer_id is null for applicants who were not customers when they applied. Write the anti-join, return segment and customer_count, and state in one line what NOT IN (SELECT customer_id FROM fct_loan_application) returns against this table and why.

Approach

1. Pin the dimension to one row per customer first: is_current = true already guarantees that, but say so out loud, because forgetting it multiplies every count by the number of attribute versions a customer has accumulated.
2. Write the anti-join as NOT EXISTS with a correlated predicate on customer_id, which evaluates per row and is unaffected by nulls anywhere in the applications table.
3. Name the failure explicitly: NOT IN against a nullable column compares each candidate to a set containing NULL, the comparison yields UNKNOWN rather than TRUE, and the whole predicate is therefore never satisfied, so the query returns zero rows.
4. If NOT IN is required for some reason, add WHERE customer_id IS NOT NULL inside the subquery, which restores the intended semantics, and note that a LEFT JOIN with an IS NULL filter is equally safe.
5. Group by segment and sanity-check the total against the unfiltered current-customer count minus the count of distinct applying customers.

Worked solution (20 min)

1. SELECT segment, COUNT(*) FROM dim_customer c WHERE c.is_current AND c.kyc_status = 'verified' AND c.closed_at IS NULL.
2. Add AND NOT EXISTS (SELECT 1 FROM fct_loan_application a WHERE a.customer_id = c.customer_id).
3. Group by segment and order by the count descending.
4. Run the NOT IN variant alongside it and record that it returns zero rows, then run it again with IS NOT NULL added to the subquery and confirm the counts match the NOT EXISTS version.

Expected result: One row per segment present in the current dimension (retail, sme, corporate), each with a non-zero customer_count. The NOT EXISTS and the null-guarded NOT IN forms agree exactly; the unguarded NOT IN form returns no rows at all.

Verify it yourself

• COUNT(DISTINCT customer_id) equals COUNT(*) on the filtered dimension, which confirms is_current really collapsed the type 2 versions.
• The total across segments plus COUNT(DISTINCT customer_id) from fct_loan_application restricted to current verified open customers equals the full current verified open customer count.
• Swapping NOT EXISTS for the unguarded NOT IN changes the result from a populated set to an empty one, which is the whole point of the exercise.

Follow-up

• Rewrite it as a LEFT JOIN with IS NULL and say when you would prefer that form to NOT EXISTS.
• How does the answer change if you want customers who never applied as of a historical date rather than today?
• The applications table has 40,000 rows with a null customer_id. What are those rows, and are they a data quality problem or a product fact?

Price a false decline when the label does not exist

Hard · proxy metrics · selection bias · randomised holdout

Your expected-cost threshold needs a figure for what a false decline costs beyond the margin on the blocked transaction. fct_payment_authorization records the decline, nothing records what the customer did next elsewhere, and declined transactions never produce a fraud outcome, so neither side of the error is directly observable. Propose the measurement: the proxy you would build from the tables you have, the design that yields an unbiased estimate for at least part of the score range, the bias in each, and the single sentence you would attach to the number when it reaches a pricing decision.

Approach

1. Write down what is unobservable and why. The counterfactual spend of a customer who was not declined, and the fraud label on any transaction the rule blocked, are both missing because of the decision itself. Missingness that depends on the decision is not fixed by matching on observed covariates.
2. Build the observational proxy anyway and be specific. For customers receiving a first risk-rule decline in a window, compare settled volume and active status over the following 30 and 90 days against customers matched on pre-period settled volume, tenure, segment and channel mix who attempted a comparable transaction and were approved. The bias runs one way: matching conditions on having attempted something that scored near the cutoff, and part of the declined group are genuine fraudsters whose disappearance is a saving rather than a loss, so the estimate overstates the damage.
3. Buy one unbiased local estimate. Hold a small random share of authorizations inside a defined risk_score band out of the decline rule and approve them, sizing the sample in advance from the expected fraud rate in that band so the cost of the experiment is known before it runs. The result is unbiased for that band only, and it is simultaneously the only source of fraud labels in the declined region.
4. Bound the extrapolation instead of hiding it. Run the holdout in two or three adjacent bands and report the spread. If the effect is flat across bands a constant is defensible; if it is steep, quote band-specific figures and decline to supply a single number.
5. Handle the window. Attrition after a decline can resolve over months, so a 90-day window truncates it and the randomised estimate is a lower bound on long-run damage at the same time as the observational version is an upper bound. Stating both directions is what makes the number safe to use.
6. Write the sentence that travels with the number: what it is (an estimate from a randomised holdout in one score band over a 90-day window), what it is not (a measurement anywhere else on the score range), and which way it is likely to be wrong.

Worked solution (40 min)

1. Define the decline cohort and the matched comparison cohort precisely, including matching variables and the pre-period window, and produce the 30-day and 90-day settled-volume difference.
2. Decompose the declined cohort into customers who never transact again and customers who transact less, since fraudsters concentrate in the first group and that split tells you how much of the estimate is contamination.
3. Write the holdout design: score band, sample share, expected fraud rate in band, expected cost of running it, and the run length needed to detect an effect large enough to change the cutoff.
4. Recompute p* = C_FP / (C_FP + C_FN) at the top and bottom of your estimated cost range and state whether the range changes the cutoff you would set.
5. Write the one-sentence caveat that will be quoted alongside the number in the pricing decision.

Expected result: Two numbers with opposite biases, an observational estimate labelled as an upper bound and a randomised in-band estimate labelled unbiased for that band only, plus a sensitivity table showing how p* moves across the range and an explicit statement of whether the residual uncertainty changes the decision.

Verify it yourself

• If the cost range moves p* by less than the granularity at which the rule can actually be set, further measurement is not worth buying and that is the finding.
• The observational estimate should exceed the randomised one in magnitude. If it does not, the matching is capturing something other than the effect of the decline and needs re-examining.
• Removing customers with zero prior settled volume from both cohorts should shrink the observational estimate, since new-account fraud concentrates there.

Follow-up

• Compliance and finance both object to deliberately approving transactions you believe are fraudulent. What is your answer, and how do you size the holdout?
• Your interval spans the decision boundary. What do you recommend?
• How would you detect that this number has gone stale?

Diagnose a sample ratio mismatch before reading the result

Easy · sample ratio mismatch · instrumentation · chi-square

A two-week test of a new risk rule logged 512,340 exposures in treatment and 508,110 in control against an intended 50/50 split. The dashboard reports a 1.8 percent relative lift in the count-weighted authorization approval rate, p equals 0.004. Exposures are written by the events pipeline at the point the rule is evaluated. Before anyone reads the lift, test whether the split is consistent with 50/50, state your verdict, rank the mechanisms that would produce this imbalance, and say what you do with the two weeks of data.

Approach

1. Run the test rather than eyeballing the ratio: a chi-square goodness-of-fit on one degree of freedom against the expected 50/50, or equivalently a binomial test on the treatment share. A 0.42 percent imbalance looks trivial and is not, because at a million exposures the null distribution is extremely tight.
2. Declare the result uninterpretable rather than adjusting it. An SRM means units are missing from one arm conditional on something, and the something is usually correlated with the outcome, so reweighting or trimming does not restore exchangeability; it just hides the selection.
3. Localise the mismatch before hypothesising about it: recompute the split by day, by channel, by issuer_country and by whether the rule actually fired. An SRM confined to one slice points straight at the code path that produced it.
4. Rank mechanisms by how often they are the cause here. First, exposure logged downstream of a step the treatment changes, so any arm-specific drop-off before the log line silently deletes units. Second, assignment keyed on something mutable or nullable, such as card_token_id across a reissue or a null customer_id on guest traffic. Third, bot or fraud filtering applied after assignment and hitting arms unequally. Fourth, retry rows deduplicated after assignment rather than before. Fifth, a ramp or a rollback that moved mid-test.
5. Close the loop with an A/A run on the fixed pipeline before rerunning the A/B, and add a continuous SRM check with an alert threshold so the next occurrence is caught on day one instead of at readout.

Follow-up

• Suppose the mismatch is entirely in one issuer_country and the treatment adds a 3-D Secure step there. What is the most likely code path, and what does that imply about the sign of the observed lift?
• What SRM alert threshold would you set for a daily check, and how do you keep it from firing constantly across many concurrent tests?
• If the split is exactly 50/50 but the two arms have different distributions of mcc and channel, is that an SRM? What is it, and what do you do about it?

Portfolio delinquency improving while the loan book doubles

Easy · vintage analysis · age mix · right censoring

The blended 90-plus days-past-due rate across fct_loan_performance_monthly fell from 3.1 to 2.2 percent over two quarters while monthly funded volume roughly doubled. Credit leadership wants to know whether underwriting improved. Columns: loan_id, as_of_month_end, origination_month, months_on_book, original_principal_minor, principal_balance_minor, days_past_due, delinquency_bucket, restructured_flag, charge_off_flag, charge_off_date. Produce the view that answers the question honestly, and state in one sentence what the blended rate can and cannot tell you.

Approach

1. Name the mechanical floor first. A first instalment falls due roughly a month after funding, so a loan cannot reach dpd_90_plus until around its fourth month on book. Every recent origination therefore enters the denominator with a numerator that is structurally zero.
2. Build a vintage table: rows origination_month, columns months_on_book, cell equal to the share of that cohort whose worst days_past_due reached 90 or more, or whose charge_off_flag became true, at or before that age.
3. Use each loan's worst state to date rather than its current bucket, and take the pre-restructure worst state, because restructuring resets days_past_due and would otherwise read as a cure.
4. Compare cohorts only at equal months_on_book, and render cells beyond a cohort's current maturity as absent rather than zero, so the table cannot be misread left to right.
5. Decompose the blended move into an age-mix component and a within-age component, so the write-up states how much of the 0.9 point improvement is arithmetic rather than asserting it.

Follow-up

• What does the diagonal of a vintage table represent, and when is reading it the right thing to do?
• How would a change in charge-off timing policy show up in this table, and how would you separate it from credit quality?
• Which single chart goes in front of the credit committee, and what do you say when someone asks for the blended series anyway?

Suggested practice checklist

For someone who has spent the last year in notebooks, dashboards or modelling work and has not written raw SQL under time pressure. The first four days rebuild query fluency against a fixture you control and can verify by hand; the last three attach that fluency to the rest of the loop.

Day 1 — Build a fixture you can check answers against

• Create a local Postgres or SQLite database with four tables (users, sessions, events, orders) holding roughly 200 rows you generated yourself, so you know the contents well enough to predict every result.
• Deliberately seed the cases that break queries: a user with no sessions, a session with no events, two orders sharing a timestamp, a NULL in one join key, and one duplicated user row.
• Before writing any SQL, hand-compute five answers on paper (how many users placed at least one order, median orders per ordering user, and three others) and save them as the ground truth for the week.

Deliverable: A one-command seed script plus a text file of five hand-computed answers to grade every later query against.

Day 2 — Joins, filters and NULL semantics

• Answer "which users have no orders" three ways (LEFT JOIN with IS NULL, NOT EXISTS, NOT IN) and confirm that the NOT IN version returns zero rows once the subquery contains a NULL, because the comparison is never TRUE.
• Reproduce the LEFT JOIN that silently collapses to an inner join by putting a right-table predicate in WHERE, then fix it by moving the predicate into the ON clause, and record both row counts.
• Create a fan-out bug on purpose by joining orders to order_items and summing the order total, then correct it with a pre-aggregated subquery and explain in one line which table changed the grain.

Deliverable: One annotated .sql file holding the three join traps, each with the wrong result and the corrected result side by side.

Day 3 — Window functions and frames

• Write three window queries against the fixture: a running order total per user, the rank of each order within its user by value, and the day gap to that user's previous order, then check each against the day-one ground truth.
• Run ROW_NUMBER, RANK and DENSE_RANK over a column containing ties, print all three side by side, and write one sentence on when each is the correct choice.
• Switch one query from the default frame (RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW, which is what you get when ORDER BY is present and no frame is written) to ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW, and explain why the output differs only when the ORDER BY column has duplicates.

Deliverable: Three verified window queries plus a short note explaining the RANGE versus ROWS difference in your own words.

Day 4 — The four analytical query patterns

• Write a monthly retention grid: first order month per user, then months-since-first as the column, and verify that month zero equals the cohort size exactly.
• Sessionize the events table under a 30-minute inactivity rule using LAG plus a cumulative sum over a new-session flag.
• Build a four-step funnel that counts distinct users rather than events at each step, and state the rule you applied to a user who reaches step three without ever logging step two.

Deliverable: One file with the retention, sessionization and funnel patterns, each carrying a one-line note on the assumption it bakes in.

Day 5 — Write SQL the way you will have to write it live

• Set a 12-minute timer and solve three medium prompts in a plain editor with no execution and no autocomplete, then run them and tally syntax errors separately from logic errors.
• Narrate one solution aloud while writing it, stating the grain of each intermediate result (one row per user, one row per user-day) before you type its body.
• Rewrite your slowest solution as a CTE chain where every CTE name states its grain, and time yourself re-solving it from blank.

Deliverable: A recording of one narrated solution plus an error tally that separates syntax from logic.

Day 6 — One day for everything that is not SQL

• Write the preconditions of the two-sample t-test from memory, then check them: independent observations, and a difference in means whose sampling distribution is approximately normal, which at large sample sizes follows from the central limit theorem rather than from normality of the raw values.
• Write the difference between an odds ratio from logistic regression and a relative risk, and state the condition under which the two are close (low outcome prevalence).
• Prepare a 90-second answer to "how would you know this model is any good" that names the metric, the baseline you would beat, and the cost of the errors you care about.

Deliverable: One page of notes covering test preconditions, the odds-ratio caveat and the model-quality answer.

Day 7 — Full loop rehearsal

• Run a 45-minute mock with someone willing to interrupt: 20 minutes of SQL, 15 minutes defining a metric, 10 minutes on a past project.
• Re-solve from blank the two queries you were slowest on this week and compare the times against day five.
• Write a five-line answer to "walk me through a project" that puts a number in the first sentence and names the decision the work changed.

Deliverable: Mock feedback notes plus a timed project narrative you can deliver without reading it.

Stories where someone disagreed with you

Have two ready. In one, the data was on your side and you had to move someone who outranked you. In the other, the pushback was correct and you changed position. The second is the harder story and it lands better, because it shows you separate being right from being attached to an answer. Name the person's actual objection.

State honestly what your cutoff change actually contributed

Hard · impact attribution · swap set · counterfactual

Six months ago your recommendation moved a credit cutoff, using fct_loan_application and fct_loan_performance_monthly. Since then approval rate rose four points and the 12-month vintage 90-plus rate on affected cohorts is flat. In the same window the bureau changed a score attribute, marketing shifted channel mix toward broker, and the internal funding rate moved. Your performance review asks for impact in currency terms. Give the number you would stand behind, the counterfactual it rests on, and the part of the observed movement you would not claim.

Approach

1. Define the counterfactual before computing anything: the claim is not what happened after the change, it is what would have happened had the old cutoff scored the same applications, which means replaying the old threshold on the post-change population.
2. Build the swap set: applications the new cutoff approves that the old one declined, applications the old one approved that the new one declines, and everyone else held out as unaffected. Only the swap groups carry your effect. Note that the swap-out group has no outcome under the new rule, because those loans were never funded, so its forgone margin must be estimated from matched pre-change approvals rather than observed.
3. Price each swap group at months_on_book equal to 12 on the measure the cutoff was meant to move: interest and fees collected, minus net charge-offs, minus funding cost at the internal transfer rate.
4. Strip the confounders explicitly. Cohorts affected by the bureau attribute change are either recomputed on the old attribute or excluded; channel mix is held fixed by reweighting to the pre-change mix; funding cost is charged at the rate in force each month rather than one blended average.
5. State the residual you will not claim, with its size, and give a range rather than a point wherever cohorts have not yet reached 12 months on book.

Follow-up

• The swap-in group is only 6 percent of applications. How does that change the way you present the number, and to whom?
• What would you have needed to set up at launch to make this attribution clean, and why was a randomised band around the cutoff not used?

Recommend a decision whose true outcome matures a year later

Hard · decision under censoring · leading indicators · staged rollout

An underwriting rule change must be decided in six weeks. Its real outcome, the vintage 90-plus rate at months_on_book 12 in fct_loan_performance_monthly, matures in a year. The executive wants a yes or no, not a range. Randomising the credit decision across the whole population is not available. Name the leading indicator you would accept, state its bias and the direction of that bias, define the decision rule and stopping condition before any rollout starts, and say what reading would make you recommend reversing the change.

Approach

1. Fix the readout before the rollout, because a readout chosen after the data arrives is a story rather than a decision rule: indicator, window, threshold and reversal condition all go in writing first.
2. Choose the leading indicator on its measured relationship to the matured outcome in historical vintages rather than on availability. Early delinquency, typically the share reaching dpd_1_29 or missing a first scheduled payment by months_on_book 3, is the usual candidate, and you quantify how well it predicted the 12-month rate across past cohorts.
3. State the bias and its direction plainly: early delinquency under-represents default that emerges later and is contaminated by servicing and payment-date effects, so treat it as a floor on risk rather than an estimate of it.
4. Buy identification where full randomisation is unavailable: a narrow randomised approval band around the cutoff, or a staged rollout by channel or region read as a difference-in-differences, with the parallel-trends assumption stated and checked in the pre-period rather than assumed.
5. Give the executive the binary they asked for with the trigger attached in the same sentence: yes, conditional on the month-3 indicator staying inside a stated band, with an automatic hold if it breaches.

Follow-up

• How would you validate that the month-3 indicator predicts the 12-month outcome, and what evidence would invalidate it mid-rollout?
• Compliance refuses a randomised band. What is your next-best identification strategy, and what precision do you lose by taking it?

Explain an incomplete dispute chart to a non-technical executive

Easy · dispute maturity · stakeholder communication · right-censoring

A finance lead is looking at first-chargeback rate by transaction month, built from fct_card_dispute joined to fct_payment_authorization on auth_id and attributed to requested_at. The last three months slope sharply down and the lead wants to announce a fraud improvement at tomorrow's review. Consumer dispute rights commonly run around 120 days from the transaction or expected delivery date, so those months are not complete. In five minutes, with no statistics vocabulary, explain why the decline is not yet evidence and say exactly what you would put on the slide instead.

Approach

1. Lead with the mechanism in the listener's own terms, not with the statistical name for it: a dispute is attributed to the month the transaction happened, but it can be filed up to roughly 120 days later, so recent months contain only the disputes filed so far.
2. Show completeness rather than arguing about the rate: for each transaction month, plot the share of its eventual disputes already filed, estimated from months that are fully matured. The last three months will sit visibly below 100 percent.
3. Replace the chart with two artefacts: a matured series that stops 120 days back and is labelled final, and a development-factor estimate for the immature months drawn as a dashed range and labelled an estimate.
4. Hand over one sentence the executive can repeat without you in the room: the recent months look better because the disputes have not arrived yet, not because fewer will arrive.
5. Offer a weekly signal they can watch instead, such as the risk-score mix of approved volume or the decline-rule hit rate, and state up front what it does and does not predict.

Follow-up

• The deck ships tomorrow regardless. What exactly goes on the slide, and what wording do you insist on?
• How would you estimate the development factors, and how would you notice if they had shifted?