What is an AUC?
A number between 0.
Stands for: Area under the ROC curve
AUC explained in plain English
A number between 0.0 and 1.0 representing a binary classification model's ability to separate positive classes from negative classes. The closer the AUC is to 1.0, the better the model's ability to separate classes from each other. For example, the following illustration shows a classification model that separates positive classes (green ovals) from negative classes (purple rectangles) perfectly. This unrealistically perfect model has an AUC of 1.0: Conversely, the following illustration shows the results for a classification model that generated random results. This model has an AUC of 0.5: Yes, the preceding model has an AUC of 0.5, not 0.0. Most models are somewhere between the two extremes. For instance, the following model separates positives from negatives somewhat, and therefore has an AUC somewhere between 0.5 and 1.0: AUC ignores any value you set for classification threshold. Instead, AUC considers all possible classification thresholds.
AUC represents the area under an ROC curve. For example, the ROC curve for a model that perfectly separates positives from negatives looks as follows: AUC is the area of the gray region in the preceding illustration. In this unusual case, the area is simply the length of the gray region (1.0) multiplied by the width of the gray region (1.0). So, the product of 1.0 and 1.0 yields an AUC of exactly 1.0, which is the highest possible AUC score. Conversely, the ROC curve for a classification model that can't separate classes at all is as follows. The area of this gray region is 0.5. A more typical ROC curve looks approximately like the following: It would be painstaking to calculate the area under this curve manually, which is why a program typically calculates most AUC values. ---
AUC is the probability that a classification model will be more confident that a randomly chosen positive example is actually positive than that a randomly chosen negative example is positive. --- See Classification: ROC and AUC in Machine Learning Crash Course for more information.
Example
Practitioners refer to auc when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.
People also read
- Backpropagation
The process that tells a neural network which internal settings caused an error and how to adjust them, working backwards through layers.
- Bayesian neural network
A probabilistic neural network that accounts for uncertainty in weights and outputs.
- Bayesian optimization
A probabilistic regression model technique for optimizing computationally expensive objective functions by instead optimizing a surrogate that quantifies the uncertainty using a Bayesian learning technique.
- BERT
A model architecture for text representation.
- classification threshold
In a binary classification, a number between 0 and 1 that converts the raw output of a logistic regression model into a prediction of either the positive class or the negative class.
- configuration
The process of assigning the initial property values used to train a model, including: hyperparameters such as: - learning rate - iterations - optimizer - loss function In machine learning projects, c
- confusion matrix
An NxN table that summarizes the number of correct and incorrect predictions that a classification model made.
- cross-entropy
A generalization of Log Loss to multi-class classification problems.
- discriminative model
A model that predicts labels from a set of one or more features.
- embedding layer
A special hidden layer that trains on a high-dimensional categorical feature to gradually learn a lower dimension embedding vector.