Fake Accounts [AE]

Quick Overview

Evaluates probability, classification metrics, and feature engineering for fake-account detection. Strong answers apply Bayes' rule with rate-weighted friend requests, compute positive predictive value under low prevalence, and propose practical account, graph, behavior, and device features.

Fake Accounts [AE]

Company: Meta

Role: Data Scientist

Category: Statistics & Math

Difficulty: medium

Interview Round: Onsite

Quick Answer: Evaluates probability, classification metrics, and feature engineering for fake-account detection. Strong answers apply Bayes' rule with rate-weighted friend requests, compute positive predictive value under low prevalence, and propose practical account, graph, behavior, and device features.

|Home/Statistics & Math/Meta
Meta logo
Meta
Jul 12, 2025, 6:59 PM
mediumData ScientistOnsiteStatistics & Math
216
0
Loading...
Loading comments...