Knowledge Graph — Coursera Notes › Academic disciplines › Information Technology / Computer Science › Artificial Intelligence › Machine Learning & Data

Accuracy

concept · part of Machine Learning & Data

A metric for classification models calculated as correct predictions divided by total predictions.

Accuracy is most useful when class distribution is balanced and the costs of false positives and false negatives are similar.

Formula: (TP+TN)/(TP+FP+TN+FN).

Accuracy can be calculated for both training and validation phases to understand model performance. Example: a model achieving 95% accuracy correctly predicts the outcome for 95% of the instances in the dataset.

Connections

• Builds on Train/test split
• Builds on Confusion matrix

This is the text view of an interactive 3D knowledge graph — open this page with JavaScript enabled to explore it visually.