4.4 Precision and Recall

Notes

Precision tell us the fraction of positive predictions that are correct. It takes into account only the positive class (TP and FP - second column of the confusion matrix), as is stated in the following formula:

$P = \cfrac{TP}{TP + FP}$

Recall measures the fraction of correctly identified positive instances. It considers parts of the positive and negative classes (TP and FN - second row of confusion table). The formula of this metric is presented below:

$R = \cfrac{TP}{TP + FN}$

In this problem, the precision and recall values were 67% and 54% respectively. So, these measures reflect some errors of our model that accuracy did not notice due to the class imbalance.

MNEMONICS:

Precision : From the predicted positives, how many we predicted right. See how the word precision is similar to the word prediction?
Recall : From the real positives, how many we predicted right. See how the word recall is similar to the word real?

Add notes from the video (PRs are welcome)

Notes from Peter Ernicke

Machine Learning Zoomcamp course
Session 4: Evaluation Metrics for Classification
Previous: Confusion table
Next: ROC Curves

Notes

P = \cfrac{TP}{TP + FP}

R = \cfrac{TP}{TP + FN}

In this problem, the precision and recall values were 67% and 54% respectively. So, these measures reflect some errors of our model that accuracy did not notice due to the class imbalance.

MNEMONICS:

Precision : From the predicted positives, how many we predicted right. See how the word precision is similar to the word prediction?

Recall : From the real positives, how many we predicted right. See how the word recall is similar to the word real?

Add notes from the video (PRs are welcome)

4.4 Precision and Recall