How do I approach Machine Learning interview questions?

Machine Learning questions require understanding of core concepts and practice. PracHub provides solutions with explanations to help you master machine learning interviews.

What difficulty level is this interview question?

This is a medium difficulty Machine Learning question, commonly asked during Onsite rounds at Meta.

What role is this question designed for?

This question is commonly asked for Data Scientist candidates at Meta during technical interviews.

Evaluate Fake-Account Classifier with Precision and Recall Metrics | Meta Interview Question

Evaluate Fake-Account Classifier with Precision and Recall Metrics

Last updated: Mar 29, 2026

Quick Overview

This question evaluates a candidate's understanding of classifier evaluation metrics (precision, recall, F1, ROC-AUC), cost-sensitive decision making, threshold tuning, and handling class imbalance for production ML systems.

Evaluating a Fake-Account Classifier in Production

Scenario

You have trained a model that flags fake accounts. Leadership wants clear, defensible evidence that it works well in production and understands the trade-offs of using it to take actions (e.g., auto-ban vs. human review).

Task

Recommend the evaluation metrics you would use to judge the fake-account classifier and explain why. Discuss the trade-offs among:

Precision, recall, F1
ROC-AUC
Business costs of false positives (blocking a real user) vs. false negatives (missing a fake)

Include in your answer:

How class imbalance affects metric choice
How you would pick and tune thresholds
How you would incorporate cost-based metric selection

Solution

Show

Comments (0)

Loading comments...

Browse More Questions

More Machine Learning•More Meta•More Data Scientist•Meta Data Scientist•Meta Machine Learning•Data Scientist Machine Learning