Your company manages a video sharing website where users can watch and upload videos. You need to create an ML model to predict which newly uploaded videos will be the most popular so that those video

Question

Options

• AThe model predicts videos as popular if the user who uploads them has over 10,000 likes.
• BThe model predicts 97.5% of the most popular clickbait videos measured by number of clicks.
• CThe model predicts 95% of the most popular videos measured by watch time within 30 days of
• DThe Pearson correlation coefficient between the log-transformed number of views after 7 days

• A
  6% (1)
• C
  83% (15)
• D
  11% (2)

Explanation

Watch time is the gold-standard engagement metric for video platforms because it measures whether users genuinely valued the content, not just whether they clicked on it. Predicting 95% of popular videos by watch time within 30 days of upload directly aligns the model's success with the business goal of surfacing quality content. Option A uses uploader reputation as a proxy, which is not predictive of individual video quality. Option B targets clickbait via click count, which is easily gamed and doesn't reflect genuine engagement. Option D uses a Pearson correlation of views after 7 days-a statistical measure that doesn't translate directly into whether the prioritization system works as intended for the business.

No community discussion yet for this question.