Design A/B Test for Short-Video Recommendation Algorithm

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 Design A/B Test for Short-Video Recommendation Algorithm states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.

Design A/B Test for Short-Video Recommendation Algorithm

Company: Meta

Role: Data Scientist

Category: Analytics & Experimentation

Difficulty: medium

Interview Round: Onsite

##### Scenario Short-video app (TikTok-like) – A/B testing a new recommendation algorithm. ##### Question List the top three metrics you’d use to measure user engagement in a short-video feed. Design an A/B test for the new recommender: specify sample-size calculation, experiment duration, and stopping criteria. ##### Hints Consider watch time per DAU, session starts, likes per view; use power analysis for size, minimum-detectable effect for duration.

Quick Answer: 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 Design A/B Test for Short-Video Recommendation Algorithm states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.

|Home/Analytics & Experimentation/Meta
Meta logo
Meta
Aug 4, 2025, 10:55 AM
mediumData ScientistOnsiteAnalytics & Experimentation
8
0

Design A/B Test for Short-Video Recommendation Algorithm

A/B Test: New Short‑Video Recommendation Algorithm

Context

You are evaluating a new recommendation algorithm for a TikTok‑like short‑video feed. The goal is to measure whether the new algorithm increases user engagement without harming experience quality.

Tasks

  1. List the top three user‑engagement metrics you would track and define them precisely.
  2. Design the A/B test, including:
    • Experiment unit and randomization.
    • Sample‑size calculation (show the power analysis).
    • Experiment duration (connect to your minimum detectable effect).
    • Stopping criteria (statistical and practical).

Constraints & Assumptions

  • Preserve the scope, facts, inputs, and requested outputs from the prompt above.
  • If the prompt leaves a detail unspecified, state a reasonable assumption before relying on it.
  • Keep the answer interview-ready: concise enough to present, but concrete enough to implement or evaluate.

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?
Loading comments...

Browse More Questions

More Analytics & Experimentation•More Meta•More Data Scientist•Meta Data Scientist•Meta Analytics & Experimentation•Data Scientist Analytics & Experimentation