3.2.2 Precision Recall Accuracy and ROC Curves of Binary Classification
We can emit two values in these kinds of problems,
yes or no
This results in four material outcomes.
- true positive
- true negative
- false positive
- false negative
Populating a table with counts of these values creates what is called a confusion matrix.
Expressing performance of these kinds of tasks comes in different forms.
Accuracy is the simplest - quantifying what percentage of the examples are classified correctly