Is our classifier doing well? Is this better than the other one? In classification, we count how many times we classify something right and wrong. Suppose there are two possible classification labels of yes and no, then there are four possible outcomes, as shown in the following table:
| Predicted as positive? | |||
| Yes | No | ||
| Really positive? | Yes | TP-True Positive | FN- False Negative |
| No | FP- False Positive | TN-True Negative | |
The four variables:
- True positive (hit): This indicates a yes instance correctly predicted as yes
- True negative (correct rejection): This indicates a no instance correctly predicted as no
- False positive (false alarm): This indicates a no instance predicted as yes
- False negative (miss): This indicates ...
