AIExplainer
Machine Learning Intermediate 2 min read

What is true negative?

A correct prediction that a condition or event is absent

In the context of AI and machine learning, a true negative refers to a situation where a model correctly predicts that a certain condition or event does not exist or will not occur. This is often used in binary classification problems, where the model is trying to distinguish between two classes, such as 'diseased' or 'not diseased'

A true negative is like a fire alarm that does not go off when there is no fire. The alarm is correctly indicating that there is no emergency, just like a true negative indicates that a certain condition is not present

A medical test for a disease that correctly indicates that a patient does not have the disease is a true negative. For example, a COVID-19 test that comes back negative for a healthy person is a true negative

True negatives are used to evaluate the performance of machine learning models, particularly in medical diagnosis, credit risk assessment, and spam detection. A high number of true negatives indicates that the model is good at avoiding false alarms

One common misconception is that a true negative is the same as a false negative. However, a false negative occurs when a model fails to detect a condition that is actually present, whereas a true negative occurs when a model correctly predicts that a condition is absent

The concept of true negatives has been around since the early days of machine learning and has been used in various fields, including medicine, finance, and engineering

correct rejection true negative prediction

Three products for different needs — explore what’s relevant to you.