Microsoft Azure AI Fundamentals (AI-900)Describe fundamental principles of machine learning on AzureMedium
A machine learning engineer is developing a model to identify spam emails. The model is trained on a large dataset of emails labeled as 'spam' or 'not spam'. After training, the engineer evaluates the model's performance. Which of the following metrics is most crucial if the primary goal is to ensure that legitimate emails are almost never incorrectly classified as spam?
- ARecall
- BF1-Score
- CPrecision
- DAccuracy
Show answer & explanationAnswer & explanation
Correct answer: C. Precision
If the goal is to minimize false positives (legitimate emails incorrectly classified as spam), Precision is the most crucial metric. High precision means that when the model predicts spam, it is almost always correct.
Why the other options are wrong
- A. Recall measures the proportion of actual positives that were correctly identified, which is important for not missing spam, but not the primary goal here.
- B. F1-Score is the harmonic mean of precision and recall, balancing both, but doesn't prioritize one over the other for this specific scenario.
- D. Accuracy measures overall correctness but doesn't specifically prioritize minimizing false positives over false negatives.
Precision (Positive Predictive Value)
The ratio of correctly predicted positive observations to the total predicted positive observations. It answers: 'Of all the times we predicted positive, how many were actually positive?'
- Focuses on minimizing False Positives.
- Important when the cost of a false positive is high.
- Calculated as True Positives / (True Positives + False Positives).
Memory trick: Every Metric Tells a Tale of Model Performance