Meta: Estimate Fake Accounts Using Data Signals and Sampling

Quick Overview

This interview question evaluates metric design, causal reasoning, experiment setup, diagnostics, SQL/statistical checks, and recommendations in a realistic interview setting. A strong answer for Estimate Fake Accounts Using Data Signals and Sampling states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.

Estimate Fake Accounts Using Data Signals and Sampling

Background

A large social platform wants to estimate the proportion and absolute count of fake accounts on the service. "Fake" includes accounts that are inauthentic (bots, impersonations, coordinated inauthentic behavior), excluding clearly legitimate users. Estimates should be produced for a defined time window (e.g., monthly) and a defined population (e.g., all accounts, or active accounts in the last 30 days).

Task

Design an analytics approach to estimate the prevalence (percentage) and count of fake accounts on Facebook. Specify:

Data signals/features you would use.
A sampling strategy for labeling and estimation.
A modeling approach to classify fakes and estimate prevalence.
A validation plan and how you would compute confidence intervals.

Hints: Consider random/stratified sampling, supervised classification with manual labeling, capture–recapture, and confidence intervals.

Clarifying Questions to Ask Guidance

Clarify the business objective, unit of analysis, time window, exposure definition, and primary metric.
State assumptions about instrumentation, randomization, sample size, and data quality.
Separate descriptive analysis from causal claims.

What a Strong Answer Covers Guidance

A metric framework with primary, guardrail, and diagnostic metrics.
A credible analysis or experiment design with clear assumptions and bias checks.
SQL/statistical logic for segmentation, variance, confidence, and data validation where relevant.
An actionable recommendation that explains trade-offs and next steps.

Follow-up Questions Guidance

What sanity checks would you run before trusting the result?
How would you handle novelty effects, seasonality, or selection bias?
What decision would you make if metrics disagree?

Estimate Fake Accounts Using Data Signals and Sampling

Quick Overview

Estimate Fake Accounts Using Data Signals and Sampling

Estimate Fake Accounts Using Data Signals and Sampling

Estimating Fake Accounts on a Social Network

Background

Task

Clarifying Questions to Ask Guidance

What a Strong Answer Covers Guidance

Follow-up Questions Guidance

Write your answer