When auditing a machine learning (ML) solution, false positives can BEST be assessed by examining the level of:

The correct answer is A. Precision. Precision is the metric that directly measures false positives. It is calculated as: Precision = True Positives / (True Positives + False Positives). A low precision score indicates a high rate of false positives - cases where the model predicted a positive outcome incorrectly…

AI Audit Planning and Execution

Question

Options

APrecision
BCompleteness
CAccuracy
DRecall

How the community answered

(39 responses)

A
90% (35)
B
5% (2)
C
3% (1)
D
3% (1)

Explanation

Precision is the metric that directly measures false positives. It is calculated as: Precision = True Positives / (True Positives + False Positives). A low precision score indicates a high rate of false positives - cases where the model predicted a positive outcome incorrectly. Recall (D) measures false negatives (missed true positives). Accuracy (C) is an overall measure that can mask false positive rates, especially in imbalanced datasets. Completeness (B) is a data quality concept, not a standard ML performance metric for evaluating false positives.

Topics

#ML Metrics#False Positives#Precision#ML Auditing

Community Discussion

No community discussion yet for this question.

Full AAIA Practice