SnowPro Advanced Data ScientistDemo

By Snowflake · Question Mode

QuestionQ36

Train and use machine learning models

To manually generate a Receiver Operating Characteristic (ROC) plot, what would a Data Scientist need to change each time before running inference again?

  • A True Positive Rate (TPR)
  • B False Positive Rate (FPR)
  • C Classification Threshold
  • D Validation Threshold
Explanation

An ROC curve plots the true positive rate against the false positive rate across different decision thresholds. Changing the classification threshold changes which scores are labeled positive, producing a new TPR/FPR point for the curve.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!