Scribd
Upload
14 views2 pages

The Receiver Operating Characteristic (ROC) Curve Offers Us A Visual

The document discusses the receiver operating characteristic (ROC) curve which plots the true positive rate against the false positive rate of a classifier. A good ROC curve stays towards the top left corner away from the diagonal line of a random classifier. The area under the ROC curve (AUC) can be used to measure a classifier's performance, with 1 being perfect and 0.5 being random.

Uploaded by

Neil KENMOE
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
14 views2 pages

The Receiver Operating Characteristic (ROC) Curve Offers Us A Visual

The document discusses the receiver operating characteristic (ROC) curve which plots the true positive rate against the false positive rate of a classifier. A good ROC curve stays towards the top left corner away from the diagonal line of a random classifier. The area under the ROC curve (AUC) can be used to measure a classifier's performance, with 1 being perfect and 0.5 being random.

Uploaded by

Neil KENMOE
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

The receiver operating characteristic (ROC) curve 

offers us a visual
approach to examine the performance of our trained classifier. It is a curve
that plots the true positive rate (TPR)of a classifier against its false positive
rate (FPR). As highlighted in the earlier section, the TPR is also known as
recall. On another hand, the FPR is the ratio of negative instances that are
wrongly predicted as positive.

A sample of the ROC curve is given below:

ROC Curve (Image prepared by author)

There is a tradeoff between the TPR and FPR — the higher the TPR, the
more FPR will be produced by the classifier. The diagonal dotted line in the
middle represents the ROC curve which is a random classifier.
The ROC curve of a good classifier should stay as far away from the
diagonal line as possible by heading towards the top left corner. Based on
this rationale, we can measure and compare our classifiers’ performance by
calculating the area under the curve (AUC) which will result in a score
called AUROC (Area Under the Receiver Operating Characteristics). A
perfect AUROC should have a score of 1 whereas a random classifier will
have a score of 0.5.

You might also like