Glossary term
Glossary term
Foundations
The number of correct classification predictions divided by the total number of predictions. That is:
For example, a model that made 40 correct predictions and 10 incorrect predictions would have an accuracy of:
Binary classification provides specific names for the different categories of correct predictions and incorrect predictions. So, the accuracy formula for binary classification is as follows:
where:
TP is the number of true positives (correct predictions).
TN is the number of true negatives (correct predictions).
FP is the number of false positives (incorrect predictions).
FN is the number of false negatives (incorrect predictions).
Compare and contrast accuracy with precision and recall.
Click the icon for details about accuracy and class-imbalanced datasets.
See Classification: Accuracy, recall, precision and related metrics in Machine Learning Crash Course for more information.
For example, a model that made 40 correct predictions and 10 incorrect predictions would have an accuracy of:
Binary classification provides specific names for the different categories of correct predictions and incorrect predictions. So, the accuracy formula for binary classification is as follows:
where:
Created for this library
A bank monitors weekly accuracy of its fraud detection model and triggers retraining whenever the seven-day rolling figure drops more than two points.
A radiology startup reports per-class accuracy of its pneumonia classifier to clinical reviewers before pilot rollout in partner hospitals.
An e-commerce search team tracks accuracy of its query intent classifier across countries to detect regional drift after each model release.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License