True and false positive and negative predictions

It’s important to understand these definitions as they form a key part of explaining other fundamental Machine Learning concepts like precision and recall.

The definitions below are outlined in the context of their application within the platform.

To start with:

• A ‘positive’ prediction is one where the model thinks that a label applies to a message
• A ‘negative’ prediction is one where the model thinks that a label does not apply to a message

True positives

A true positive result is one where the model correctly predicts that a label applies to a message.

True negatives

A true negative result is one where the model correctly predicts that a label does not apply to a message.

False positives

A false positive result is one where the model incorrectly predicts that a label applies to a message, when in fact it does not apply.

False negatives

A false negative result is one where the model incorrectly predicts that a label does not apply to a message, when in fact it does apply.

To understand each of these concepts in more detail, please see here.