Skip to Content

AI-900: Why accuracy is not always the best metric for assessing model performance

Accuracy is a popular metric for evaluating classification models, but it is not always the best measure for assessing model performance. Learn why and what other metrics to use instead.

Table of Contents

Question

Accuracy is always the primary metric used to measure a model’s performance. True or False?

A. True
B. False

Answer

B. False

Explanation

There are different metrics that can be used to measure a model’s performance.

The statement “Accuracy is always the primary metric used to measure a model’s performance” is False. While accuracy is a popular metric for evaluating classification models, it is not always the best measure for assessing model performance. For instance, accuracy can be unreliable when the class distribution is imbalanced. In such cases, other metrics such as precision, recall, F1 score, and AUC-ROC are more appropriate. Moreover, accuracy does not account for the cost of false positives and false negatives, which can be significant in certain applications. Therefore, it is important to choose the right evaluation metric based on the problem at hand and the characteristics of the data.

Microsoft Azure AI Fundamentals AI-900 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Microsoft Azure AI Fundamentals AI-900 exam and earn Microsoft Azure AI Fundamentals AI-900 certification.

Microsoft Azure AI Fundamentals AI-900 certification exam practice question and answer (Q&A) dump