Classification - Confusion Matrix & Metrics
3 important questions on Classification - Confusion Matrix & Metrics
Draw and label the confusion matrix for binary classification.
Predicted PositivePredicted NegativeActual PositiveTrue Positive (tp)False Negative (fn) — Type II errorActual NegativeFalse Positive (fp) — Type I errorTrue Negative (tn)
- Type I error (False Positive): said yes, was no
- Type II error (False Negative): said no, was yes
Write the formulas for Accuracy, Error Rate, Precision, Recall, and False-Positive Rate.
- Accuracy = (tp + tn) / (tp + fp + fn + tn)
- Error Rate = (fp + fn) / (tp + fp + fn + tn) = 1 − Accuracy
- Precision = tp / (tp + fp)
- Recall (TPR) = tp / (tp + fn)
- False-Positive Rate (FPR) = fp / (fp + tn)
What is the F1-score (F-measure)? What problem does it solve?
The F1-score is the harmonic mean of precision and recall:
F1 = (2 · Precision · Recall) / (Precision + Recall)
It solves the problem that precision and recall trade off against each other. A model that achieves high precision by rarely predicting "positive" will have low recall, and vice versa. The F1-score penalises extreme imbalance — it is high only when both precision and recall are high.
F1 = (2 · Precision · Recall) / (Precision + Recall)
It solves the problem that precision and recall trade off against each other. A model that achieves high precision by rarely predicting "positive" will have low recall, and vice versa. The F1-score penalises extreme imbalance — it is high only when both precision and recall are high.
The question on the page originate from the summary of the following study material:
- A unique study and practice tool
- Never study anything twice again
- Get the grades you hope for
- 100% sure, 100% understanding
Remember faster, study better. Scientifically proven.
