Articles → MACHINE LEARNING → Confusion Matrix In Machine Learning

Confusion Matrix In Machine Learning

This article describes the Confusion matrix in Machine Learning.

Purpose

A confusion matrix (also called an error matrix) is a table used to evaluate the performance of a classification algorithm. In other words, a confusion matrix shows how often a classification model's predictions are correct or incorrect by comparing the predicted values with the actual values.

Confusion Matrix

Total Population = P + N	Predicted: Positive	Predicted: Negative
Actual: Positive	True Positive (TP)	False Negative (FN)
Actual: Negative	False Positive (FP)	True Negative (TN)

Let us describe each outcome in the above table.

Outcome	Description
True Positive (TP)	The actual classification is positive, and the predicted classification is also positive.
False Negative (FN)	The actual classification is positive, and the predicted classification is negative.
False Positive (FP)	The actual classification is negative, and the predicted classification is positive.
True Negative (TN)	The actual classification is negative, and the predicted classification is negative.

Example

Suppose you tested the model on 100 emails. Out of 100 emails, 40 are spam, and 60 are non-spam. Your model predicted 35 spams correctly, 5 spams incorrectly (missed spam → predicted as not spam), 10 non-spams incorrectly (predicted as spam), and 50 non-spams correctly.

The confusion matrix table is: -

	Predicted: Spam	Predicted: Not Spam
Actual: Spam	35 (TP)	5 (FN)
Actual: Not Spam	10 (FP)	50 (TN)

Classification Accuracy

Classification Accuracy is the ratio of the number of correct predictions to the total number of predictions made.

In the example above, the Accuracy would be: -

35+50/35+50+10+5 = 85/100 = 0.85

Posted By -	Karan Gupta

Posted On -	Monday, June 9, 2025

Updated On -	Thursday, December 18, 2025

Query/Feedback

Your Email Id		**

Subject		*

Query/Feedback	Characters remaining 250	**