Determine Metrics for Evaluating Homepage Recommendation Carousel

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 Determine Metrics for Evaluating Homepage Recommendation Carousel states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.

Determine Metrics for Evaluating Homepage Recommendation Carousel

Company: TikTok

Role: Data Scientist

Category: Analytics & Experimentation

Difficulty: medium

Interview Round: Onsite

##### Scenario Product team launches an A/B test introducing a new recommendation carousel on the homepage. ##### Question What primary and secondary metrics would you track to evaluate the experiment? Describe the decision framework you would use to determine whether to roll the feature out to all users. ##### Hints Discuss click-through rate, conversion, guardrails, power, practical significance.

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 Determine Metrics for Evaluating Homepage Recommendation Carousel states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.

|Home/Analytics & Experimentation/TikTok
TikTok logo
TikTok
Aug 4, 2025, 10:55 AM
mediumData ScientistOnsiteAnalytics & Experimentation
2
0

Scenario

A product team has shipped an A/B test for a new recommendation carousel placed on the app's homepage. Users are randomly assigned at the user level to Control (no carousel) or Treatment (homepage shows the carousel). The goal is to improve user engagement and downstream conversions without harming overall experience or performance.

Task

  1. Propose the primary metric(s) and secondary metric(s) you would track to evaluate the experiment.
  2. Describe a clear decision framework to determine whether to roll the feature out to all users, including how you will handle statistical power, practical significance, and guardrails.

Assume a standard 50/50 split, sticky assignment, and at least one weekly cycle of traffic.

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...