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.

Identify Fake Accounts Using Machine Learning Techniques

Last updated: Mar 29, 2026

Quick Overview

This question evaluates competencies in applied machine learning for detecting fake accounts on social networks, covering feature engineering, handling class imbalance and noisy labels, model selection, evaluation metrics, and production deployment considerations.

Context

You are a data scientist at a large social platform. The goal is to detect and mitigate fake or abusive accounts while minimizing harm to legitimate users. Fake accounts are rare compared to legitimate ones, so class imbalance, noisy labels, and high business costs of mistakes are central concerns.

Tasks

End-to-end approach: Describe how you would design an end-to-end system to identify fake accounts.
Data and labels: Explain how you would obtain training labels and address label noise and class imbalance.
Features: Propose key feature families and give examples for each.
Modeling and training: Outline model choices, training setup, handling imbalance, and how you’d prevent leakage and drift.
Evaluation and prioritization: Specify offline and online evaluation metrics, how you would set thresholds, and how you would prioritize precision vs. recall given business costs.

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

Identify Fake Accounts Using Machine Learning Techniques

Last updated: Mar 29, 2026

Quick Overview

Context

Tasks

End-to-end approach: Describe how you would design an end-to-end system to identify fake accounts.
Data and labels: Explain how you would obtain training labels and address label noise and class imbalance.
Features: Propose key feature families and give examples for each.
Modeling and training: Outline model choices, training setup, handling imbalance, and how you’d prevent leakage and drift.
Evaluation and prioritization: Specify offline and online evaluation metrics, how you would set thresholds, and how you would prioritize precision vs. recall given business costs.

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

Identify Fake Accounts Using Machine Learning Techniques

Quick Overview