← Meta Interview Insights

Meta·Software Engineer·Technical Phone Screen·Intermediate

Intermediate
Jul 2026

Summary

A data science interview at Meta with a product manager asking a statistics question about user behavior distributions. Pretty short and focused, just the one question from what I remember.

Questions Asked (1)

Q1

How would you describe the distribution of daily minutes spent on Facebook per user?

Product Analytics & MetricsData Modeling
Author's notes

This sounds like a warmup but it really isn't.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by clarifying the metric definition and user scope, then describe the distribution shape using key statistical properties, and finally discuss factors that drive the shape and how you would validate it with data. Emphasize that daily minutes on Facebook is typically right-skewed with a long tail, not a normal distribution.

Pro tip: Acknowledge that the distribution is likely multimodal due to different user segments (e.g., casual vs. power users) and that median and percentiles are more informative than the mean for skewed data. Mentioning that you would segment by user type or platform shows product sense and analytical maturity.

1. Clarify the metric and scope

Define what 'daily minutes spent on Facebook per user' means: is it time spent actively engaging, or including passive scrolling? Specify the user population (e.g., global daily active users) and time frame.

2. Describe the expected distribution shape

State that the distribution is right-skewed with a long tail: most users spend a moderate amount (e.g., 10-30 minutes), while a small fraction spends hours. It may be multimodal due to different usage patterns.

3. Highlight key statistical properties

Discuss that the mean is pulled up by heavy users, so median and percentiles (e.g., 50th, 90th, 99th) better represent typical usage. Mention variance and skewness.

4. Explain drivers of the distribution

Identify factors that create the shape: user demographics, platform (mobile vs. desktop), feature usage (e.g., video, messaging), and external events (e.g., holidays).

5. Outline validation and implications

Describe how you would validate the distribution with data (e.g., histogram, log-normal fit) and discuss product implications, such as targeting power users or improving engagement for casual users.

Key Points to Mention

  • Right-skewed distribution with a long tail
  • Mean vs. median: median is more robust to outliers
  • Potential multimodality due to user segments
  • Use of percentiles to describe spread
  • Factors influencing distribution: demographics, platform, features
  • Validation through data visualization and statistical tests

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.