A true positive is a positive-class observation correctly predicted as positive. In a binary classification confusion matrix, it is the count where the true label and predicted label are both 1. section 5.2.4 section 6.3.4
Use true positives to:
- Count correct positive predictions by filtering records whose actual and predicted labels both equal 1. section 5.2.4
- Compute sensitivity or recall as tp divided by tp plus fn. section 5.2.4
- Interpret class-specific performance alongside true negatives, false positives, and false negatives rather than relying only on overall accuracy. section 6.3.4
Raisin classification
Among Besni raisins labeled 1, the logistic regression correctly predicted 384 as Besni, producing 384 true positives. The same confusion matrix also records 397 true negatives, 53 false positives, and 66 false negatives. section 5.2.4
Table 5.1 Confusion matrix for raisin classification. A confusion matrix stores classification metrics from a regression with actual and predicted binary outcomes.
|
Predicted
|
|||
|---|---|---|---|
|
Kecimen (0)
|
Besni (1)
|
||
|
Actual
|
Kecimen (0)
|
tn
|
fp
|
|
Besni (1)
|
fn
|
tp
|
|
The confusion matrix locates true positives at the intersection of actual positive and predicted positive outcomes. section 5.2.4

