314,552 interview questions from 6,000+ companies.
Tests prioritization under pressure, including trade-off judgment, stakeholder communication, and ownership of outcomes.
Explain how supervised and unsupervised learning differ, and ground the distinction in a practical ML example.
Tests adaptability under changing requirements, including reprioritization, ownership, and execution in ambiguity.
Explain the bias-variance tradeoff and how it guides model choice, regularization, and generalization performance.
Explain how INNER JOIN and LEFT JOIN differ, and when to use each for matched-only versus all-left-row analysis.
Explain precision, recall, F1-score, and ROC-AUC for a classification model.
Explain precision versus recall in plain language and how the tradeoff affects product decisions.
Assess whether a large train-to-validation gap indicates overfitting in an imagery triage classifier and recommend how to validate it.
Determine whether Data Society's course completion model is overfitting by comparing train, validation, and test metrics to a simpler baseline.
Build a predictive maintenance classifier to identify manufacturing equipment likely to fail within 7 days using sensor and maintenance data.
How to validate a model's real-world performance beyond offline metrics, with calibration and threshold decisions tied to production outcomes.
Approach for evaluating and monitoring a model so performance holds up on unseen operational data.
Build an imbalanced binary classifier for rare spacecraft telemetry faults using weighted tree models and threshold-based evaluation.
Decide whether aircraft maintenance prediction should be framed as classification or regression, then build and evaluate one model for each target.
