Data Scientist Interview Questions

Showing 481–510 of 1076 results

• HHuluMedium·Data Scientist
  Design and Monitor a Multi-Country Parameter Experiment

  This question tests the ability to design an A/B test across multiple regions while accounting for sample size requirements, variance reduction techniques, and sequential monitoring protocols.

  Analytics & ExperimentationTechnical ScreenA/B TestingPower AnalysisCUPED
• HHuluMedium·Data Scientist
  Interpret a Streaming Regression Without Overstating Causality

  This problem tests your ability to interpret multivariate regression results for product stakeholders, specifically focusing on distinguishing correlation from causation and identifying risks like collider bias.

  Analytics & ExperimentationTechnical ScreenRegressionCausal InferenceExperimental Design
• IBMEasy·Data Scientist
  Design a lead-scoring model

  Design an end-to-end lead-scoring model for a marketing/growth data science team: define the label and scoring time, engineer leakage-safe features, compare a logistic-regression baseline with gradient-boosted trees, and evaluate with capacity-aware ranking metrics. The question also probes multicollinearity, model interpretability (SHAP/reason codes), routing-threshold design, and operational risks like selection bias, class imbalance, fairness, and drift.

  Machine LearningTechnical Screen
• IBMEasy·Data Scientist
  Estimate free-trial conversion probability

  This question evaluates a data scientist's competency in cohort definition, censored-data handling, segmentation and confounding assessment, and uncertainty quantification for measuring free-trial to paid conversion, and it belongs to the Analytics & Experimentation domain within data science.

  Analytics & ExperimentationTechnical Screen
• IBMEasy·Data Scientist
  How do you detect and fix multicollinearity?

  This question evaluates understanding of multicollinearity and related competencies in regression diagnostics, feature engineering, model interpretability, and the trade-offs between coefficient inference and predictive performance.

  Statistics & MathTechnical Screen
• ImcEasy·Data Scientist
  Find valid range of q for outcome probabilities

  This question tests the ability to solve a system of linear inequalities derived from probability constraints, requiring an understanding of basic arbitrage-free pricing principles.

  Software Engineering FundamentalsTechnical ScreenProbabilityInequalitiesFinance
• InstacartMedium·Data Scientist
  Aggregate weekly revenue and attribute 4% drop

  This question evaluates a candidate's ability to perform time-based revenue aggregation, filtering, percent-change calculation, and geo-level attribution using SQL or Python, with attention to ISO-week alignment and revenue computation.

  Data Manipulation (SQL/Python)Technical Screen
• InstacartMedium·Data Scientist
  Calculate Weekly Revenue and Order Count for Standard Deliveries

  This question evaluates proficiency in time-based aggregations and filtering on order-level transactional data to compute weekly revenue and order counts specifically for standard delivery orders.

  Data Manipulation (SQL/Python)Technical Screen
• InstacartEasy·Data Scientist
  Design a pricing experiment with network effects

  This question evaluates experimental design and causal inference competencies for a two-sided marketplace pricing change, including handling network effects/interference, choice of unit of randomization and treatment markets, metric selection and diagnostics, power/MDE estimation, and operational risk assessment within the Analytics & Experimentation domain for a Data Scientist role. It is commonly asked to assess practical application of randomized and quasi-experimental methods across heterogeneous geographies and operational constraints, requiring both hands-on experimental design skills and conceptual understanding of bias, spillovers, and diagnostic metrics.

  Analytics & ExperimentationTechnical Screen
• InstacartEasy·Data Scientist
  How to debug an apparent D14 retention drop

  This question evaluates competency in cohort-based retention analysis, understanding metric maturity and right-censoring, performing data quality and definition checks, and localizing real declines across segments, releases, or funnel changes.

  Analytics & ExperimentationTechnical Screen
• InstacartEasy·Data Scientist
  How would you investigate a metric decline?

  This question evaluates a data scientist's competency in diagnostic analytics, metric instrumentation awareness, causal reasoning, and segmentation-driven problem localization for consumer marketplace KPIs.

  Analytics & ExperimentationTechnical Screen
• InstacartMedium·Data Scientist
  Investigate Instacart Revenue Decline Using Weekly Data

  Instacart analytics prompt on investigating a 4% weekly revenue decline, covering time-series anomaly detection, seasonality, changepoints, prediction intervals, and richer-data decomposition by orders, AOV, geography, cohorts, and categories.

  Analytics & ExperimentationTechnical Screen
• InstacartEasy·Data Scientist
  Investigate marketplace metrics and experiment rollout

  This question evaluates competency in marketplace analytics, causal inference, experimentation design, metric instrumentation, cohort and retention analysis, and trade-off reasoning between core business metrics and secondary signals.

  Analytics & ExperimentationTechnical Screen
• InstacartMedium·Data Scientist
  Recommend and validate a budget allocation strategy

  This question evaluates a data scientist's competency in budget allocation, experimental design, KPI definition, segmentation, and causal inference by requiring translation of SQL-derived spend and profitability insights into constrained program- and advertiser-level budget rules while managing concentration risk.

  Analytics & ExperimentationTechnical Screen
• InstacartMedium·Data Scientist
  Write SQL to rank advertisers and profitability

  This question evaluates a candidate's ability to perform ANSI SQL data transformations including unpivoting denormalized tables, aggregations, joins, and financial metric calculations such as net profit and profit margin while handling nulls and tie-breaking rules.

  Data Manipulation (SQL/Python)Technical Screen
• IEIntercontinental ExchangeMedium·Data Scientist
  Analyze Newton-Raphson Convergence, Choose Sigma, and Derive Vega

  This question evaluates numerical root-finding and option pricing competencies, specifically understanding Newton–Raphson convergence properties, implied volatility inference under the Black–Scholes model, and option sensitivity (Vega).

  Statistics & MathTechnical Screen
• IntuitMedium·Data Scientist
  Build 30-day retention cohort table

  This problem tests your ability to aggregate user activity data to calculate 30-day retention rates, requiring joins, date arithmetic, and windowing functions.

  Analytics & ExperimentationTechnical ScreenSQLRetentionCohort Analysis
• IntuitMedium·Data Scientist
  Build cohort 30-day retention from signup date

  This problem tests your ability to manipulate time-series data to calculate cohort-based user retention rates while handling data censoring constraints.

  Analytics & ExperimentationTechnical ScreenSQLPandasRetention
• IntuitMedium·Data Scientist
  Compute monthly new subscribers and YoY deltas

  This question evaluates proficiency in SQL time-series aggregation and cohort identification, including generating a month spine, computing year-over-year deltas, handling nulls and division-by-zero, and identifying partial months via a data watermark.

  Data Manipulation (SQL/Python)Technical Screen
• IntuitEasy·Data Scientist
  Design an experiment for pricing page redesign

  This question evaluates a candidate's competency in experiment design, causal inference, impact sizing, metric framework development, and statistical analysis in the context of a pricing page redesign that adds an annual subscription option.

  Analytics & ExperimentationTechnical Screen
• IntuitMedium·Data Scientist
  Engineer and Impute ZIP Features

  This Intuit data scientist machine learning screen evaluates feature engineering from address/ZIP data, joining external census-style datasets, high-cardinality encoding, and missing-ZIP imputation. It also tests awareness of fairness, privacy, leakage, and how to validate whether geographic features actually improve a model.

  Machine LearningTechnical Screen
• IntuitMedium·Data Scientist
  Exclude free subscribers via anti-join

  This question evaluates competency with SQL anti-joins, join semantics, deduplication, and correct pre-aggregation filtering to prevent excluded entities from affecting aggregated monthly and year-over-year metrics; it is categorized as Data Manipulation (SQL/Python) for a Data Scientist role.

  Data Manipulation (SQL/Python)Technical Screen
• IntuitEasy·Data Scientist
  Pivot daily users and revenue by platform

  This question evaluates data manipulation and aggregation skills, specifically computing distinct user counts and revenue aggregates and reshaping results by platform; it is in the Data Manipulation (SQL/Python) domain and assesses practical application rather than purely conceptual understanding.

  Data Manipulation (SQL/Python)Technical Screen
• J.P. MorganEasy·Data Scientist
  Compute expected value of simple gambling games

  This problem tests your understanding of expected value, probability distributions, and the mechanics of independent trials in simple gambling games.

  Software Engineering FundamentalsTechnical ScreenProbabilityStatisticsExpected Value
• J.P. MorganMedium·Data Scientist
  Explain Overfitting and Transformer Basics

  This question tests your conceptual understanding of model generalization, the mechanics of the Transformer architecture, and the trade-offs involved in sequence modeling.

  Machine LearningTechnical ScreenDeep LearningTransformersBias-Variance Tradeoff
• J.P. MorganMedium·Data Scientist
  Implement Integer Square Root

  This question evaluates numerical algorithm design and integer arithmetic competence, including robustness for edge cases and overflow handling, and is categorized in the Coding & Algorithms domain.

  Coding & AlgorithmsTechnical Screen
• J.P. MorganMedium·Data Scientist
  Implement KNN from Scratch

  This problem tests your ability to implement the K-Nearest Neighbors (KNN) algorithm from scratch, focusing on distance computation, sorting, and majority voting logic.

  Coding & AlgorithmsTechnical ScreenKNNSupervised LearningAlgorithms
• JGJain GlobalEasy·Data Scientist
  Define the p-Value, Then Explain How to Test Two Price Series for Cointegration

  Two statistics questions from a systematic trading screen: give a precise definition of the p-value and its common misreadings, then explain what cointegration is and how to test two price series for it. It tests hypothesis-testing rigor, stationarity, the difference between correlation and cointegration, and multiple-testing pitfalls.

  Statistics & MathTechnical Screen
• JJefferiesEasy·Data Scientist
  How to compute correlation from variances

  Practice deriving correlation from variance identities for two random variables. The solution explains why Var(X+Y) and Var(X) alone are insufficient, derives covariance and correlation when Var(Y) is known, simplifies the equal-variance case, and checks edge cases where correlation is invalid or inconsistent.

  Statistics & MathTechnical Screen
• JJefferiesMedium·Data Scientist
  How to derive correlation from variances

  Evaluates derivation of correlation from variance identities for two random variables. Strong answers explain why Var(X+Y) and Var(X) alone do not identify correlation, then derive covariance and correlation when Var(Y) is also known.

  Statistics & MathTechnical Screen