Katkat
Back

Evaluate Fake-Account Classifier with Precision and Recall Metrics

MetaData Scientist · Onsite
MediumData ScientistOnsiteMachine Learning

Last updated

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.

Scenario

You have built a model that flags fake accounts; leadership wants evidence it works well in production.

Question

Which evaluation metrics would you choose to judge the fake-account classifier and why? Explain the trade-offs among precision, recall, F1, ROC-AUC, and business costs of false positives versus false negatives.

Hints

Discuss class imbalance, threshold tuning, and cost-based metric selection.