practice a little every day, paws crossed ♡
Data Scientist Interview Questions
Practice 9403 coding, system design and machine learning questions from 546 companies, sorted by role, topic and interview round. Every question has step-by-step hints, a code runner that supports 8 languages and an AI mentor; members also get the full solution walkthrough.
- 9403
- Questions
- 546
- Companies
- 11
- Topics
- 8
- Languages
Showing 361–390 of 641 results
- MetaEasyData ScientistDesign metrics to detect harmful content and fraud
This problem tests the ability to design robust monitoring metrics for detecting fraudulent user activity and policy-violating content, focusing on trade-offs between precision and recall.
Analytics & ExperimentationOnsiteAnalyticsMetricsFraud-Detection - MetaMediumData ScientistDetect and address Simpson’s paradox
This question evaluates understanding of aggregation bias and Simpson's paradox, proficiency with stratified or mixed-model estimators, heterogeneity testing, and experiment decisioning within Analytics & Experimentation for a Data Scientist role.
Analytics & ExperimentationOnsite - MetaHardData ScientistDetect leakage and evaluate a prediction model
This question evaluates competence in production-ready supervised machine learning—detecting and repairing data leakage in logs-based features, designing time-aware cross-validation, defining KPI-driven thresholding and calibration, interpreting model coefficients, and establishing monitoring and retraining policies for a churn prediction model in the Machine Learning domain. It is commonly asked because interviewers need to assess both conceptual understanding of leakage, validation, and calibration principles and practical application skills for deploying and maintaining models with cost-sensitive objectives and monitoring in production, so the level of abstraction spans conceptual reasoning and hands-on practical application.
Machine LearningOnsite - MetaHardData ScientistDetermine Key Metrics and Design A/B Test for Ad Ranking
This interview question evaluates metric design, causal reasoning, experiment setup, diagnostics, SQL/statistical checks, and recommendations in a realistic interview setting. A strong answer for Determine Key Metrics and Design A/B Test for Ad Ranking states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.
Analytics & ExperimentationOnsite - MetaMediumData ScientistDetermine Metrics to Evaluate Notification Impact on Users
Evaluates product analytics judgment for Facebook push notifications, including how to measure helpful versus harmful notifications, design an event-notification experiment, and balance short-term clicks against retention, fatigue, and opt-out guardrails. Strong answers build a metric hierarchy and use causal measurement.
Analytics & ExperimentationOnsite - MetaMediumData ScientistDetermine Old vs. New Users' Shop Visibility Changes
This question evaluates SQL-focused data manipulation skills and analytical competency in cohort definition and metric selection for comparing behavioral propensities, specifically assessing how to measure the likelihood of old versus new users switching a shop profile to invisible.
Data Manipulation (SQL/Python)Onsite - MetaEasyData ScientistDetermine Posterior Probability of Bad User Prediction
Meta Bayes theorem question on a bad-actor classifier, covering prevalence, sensitivity, specificity, false positives, positive predictive value, and the base-rate effect.
Statistics & MathOnsite - MetaMediumData ScientistDetermine Probability of Fourth Good Response After Three Successes
This interview question evaluates statistical assumptions, formulas, estimation strategy, uncertainty, edge cases, and interpretation in a realistic interview setting. A strong answer for Determine Probability of Fourth Good Response After Three Successes states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.
Statistics & MathOnsite - MetaEasyData ScientistDetermine Probability of Friend Request Being Fake
Determine Probability of Friend Request Being Fake evaluates statistical assumptions, formulas, estimation strategy, uncertainty, edge cases, and interpretation in a realistic interview setting. A strong answer states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.
Statistics & MathOnsite - MetaMediumData ScientistDetermine Unhealthy Oculus Usage with SQL Analysis
This question evaluates SQL-based data manipulation and time-series analysis competencies, including sessionization, user-day aggregation, and detection of sustained behavioral patterns in event data; it is categorized under Data Manipulation (SQL/Python) and targets practical application skills.
Data Manipulation (SQL/Python)Onsite - MetaMediumData ScientistEnsure Effective Teamwork Amid Conflicting Stakeholder Opinions
This interview question evaluates behavioral evidence, ownership, communication, trade-offs, and measurable outcomes in a realistic interview setting. A strong answer for Ensure Effective Teamwork Amid Conflicting Stakeholder Opinions states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.
Behavioral & LeadershipOnsite - MetaHardData ScientistEstimate CTR lift with binomial tests and errors
This question evaluates statistical inference for proportions, sequential monitoring, and multiple-comparison error control—assessing competence with binomial-based CTR comparison, pooled standard errors, z-tests and confidence intervals, Type I error inflation from peeking, and FWER/FDR considerations.
Statistics & MathOnsite - MetaMediumData ScientistEstimate Lift and Significance in Facebook Ad Campaigns
Meta statistics prompt on Facebook ad conversion lift, covering absolute and relative lift, two-proportion tests, confidence intervals, power for 5% relative lift, and Bayesian beta-binomial reframing.
Statistics & MathOnsite - MetaMediumData ScientistEstimate bots and CI from DAU spike
This question tests the ability to decompose a mixture of legitimate user traffic and synthetic bot/CI traffic using statistical modeling, and requires justifying the choice of distribution for overdispersed count data.
Statistics & MathOnsiteMixture ModelsNegative BinomialBootstrapping - MetaMediumData ScientistEstimate fake-account prevalence with capture-recapture
This question tests the ability to apply the Lincoln-Petersen estimator to estimate a hidden population size and addresses the limitations of the assumptions underlying capture-recapture methods.
Statistics & MathOnsiteStatisticsEstimationInference - MetaHardData ScientistEstimate revenue of organic shopping tab
This question evaluates a data scientist's skills in revenue modeling, funnel construction, causal inference for bias correction, experimentation scaling, and sensitivity analysis using organic engagement and purchase metrics.
Analytics & ExperimentationOnsite - MetaHardData ScientistEstimate variance for ratio metrics
This question evaluates statistical inference and experimental-analysis skills for data scientists, including variance estimation for ratio metrics via the delta method, covariance estimation from sample moments, model-based comparisons (ANCOVA/log models with offsets), bootstrap and t-test inference considerations, and robustness techniques for heavy-tailed revenue such as winsorization and robust M-estimators. It is commonly asked to assess both theoretical derivation and practical estimation trade-offs in A/B or experimental settings; the category is Statistics & Math and the level of abstraction spans conceptual understanding and practical application.
Statistics & MathOnsite - MetaMediumData ScientistEvaluate AI-assisted ad creation
This question evaluates competency in product analytics, experimentation design, causal inference, metric definition, and measurement of downstream business and user-quality impacts for an AI-assisted advertising feature.
Analytics & ExperimentationOnsite - MetaEasyData ScientistEvaluate AI-assisted ads creation feature
This question assesses the ability to design an A/B test for a new AI feature, focusing on metric definition, experiment design, and mitigating potential trade-offs between advertiser efficiency and ad quality.
Analytics & ExperimentationOnsiteA/B TestingProduct MetricsExperiment Design - MetaHardData ScientistEvaluate Factors Before Replacing Recommendation Model
Evaluates whether an ads recommendation model should replace an existing production model. Strong answers combine offline validation, online experiments, revenue and advertiser outcomes, user guardrails, conflicting metric interpretation, rollout safety, rollback planning, and executive communication.
Machine LearningOnsite - MetaMediumData ScientistEvaluate Fake-Account Classifier with Precision and Recall Metrics
This interview question evaluates core ML concepts, assumptions, math intuition, training/evaluation trade-offs, and practical failure modes in a realistic interview setting. A strong answer for Evaluate Fake-Account Classifier with Precision and Recall Metrics states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.
Machine LearningOnsite - MetaMediumData ScientistEvaluate Instagram's Short-Video Recommender System Success
Evaluates success metrics and experimentation for Instagram's short-video recommender feed. Strong answers choose a durable user-value metric, understand heavy-tailed engagement distributions, handle metric trade-offs, and outline a safe A/B test with retention, safety, creator, and app-level guardrails.
Analytics & ExperimentationOnsite - MetaMediumData ScientistEvaluate Marketing Campaign's Click-Through Rate Effectiveness
This interview question evaluates statistical assumptions, formulas, estimation strategy, uncertainty, edge cases, and interpretation in a realistic interview setting. A strong answer for Evaluate Marketing Campaign's Click-Through Rate Effectiveness states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.
Statistics & MathOnsite - MetaHardData ScientistEvaluate Messenger's P2P Payments Feature for Business Viability
Evaluates business viability for a Messenger P2P payments feature. Strong answers define networked adoption and transfer metrics, assess fraud, compliance, support, trust, and unit economics, and propose a beta or experiment design that handles spillovers and contamination.
Analytics & ExperimentationOnsite - MetaHardData ScientistEvaluate New Ad Model with A/B Testing Experiment
This interview question evaluates metric design, causal reasoning, experiment setup, diagnostics, SQL/statistical checks, and recommendations in a realistic interview setting. A strong answer for Evaluate New Ad Model with A/B Testing Experiment states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.
Analytics & ExperimentationOnsite - MetaMediumData ScientistEvaluate Probability of Positive User Comments and Model Performance
Evaluate Probability of Positive User Comments and Model Performance evaluates statistical assumptions, formulas, estimation strategy, uncertainty, edge cases, and interpretation in a realistic interview setting. A strong answer states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.
Statistics & MathOnsite - MetaMediumData ScientistEvaluate a New Ads-Ranking Algorithm
This question tests the ability to design a robust A/B test for an ads-ranking system while accounting for interference effects, budget constraints, and conflicting metric signals.
Analytics & ExperimentationOnsiteA/B TestingAd-TechMetrics - MetaMediumData ScientistEvaluate fake accounts and ad creation
This question tests the ability to design an evaluation framework for identifying malicious actors in an ad-tech environment and measuring the performance of automated content generation tools.
Analytics & ExperimentationOnsiteAnalyticsExperimentationMetric Design - MetaHardData ScientistEvaluate the Health of Facebook Groups
Evaluates Facebook Group health metrics and threaded-comments experiment design. Strong answers define normalized health scores, compare small and large groups fairly, and test deep interaction with safety guardrails.
Analytics & ExperimentationOnsite - MetaEasyData ScientistExplain Central Limit Theorem's Importance in A/B Testing
Evaluates understanding of the Central Limit Theorem and confidence intervals in A/B testing. Strong answers explain sampling distributions, standard error, normal approximations for experiment metrics, caveats for dependence and heavy tails, and compute the 95% confidence interval as [2.902, 3.098].
Statistics & MathOnsite
Meta