AIExplainer
Machine Learning Intermediate 2 min read

What is true positive rate?

The proportion of actual positive cases that are correctly identified as positive

The true positive rate is a measure of how well a model or test can detect actual positive cases, such as diseases or defects. It is the number of true positives divided by the sum of true positives and false negatives.

Think of a security system that detects intruders. The true positive rate is like the percentage of actual intruders that the system correctly identifies, rather than letting them in or falsely accusing innocent people.

In medical diagnosis, a true positive rate of 90% means that 90% of people who actually have a disease are correctly diagnosed as having it, while 10% are missed.

The true positive rate is used to evaluate the performance of models or tests in various fields, such as medicine, finance, and quality control. It helps to identify the effectiveness of a model in detecting actual positive cases.

A common misconception is that a high true positive rate is the only measure of a model's performance. However, it is also important to consider the false positive rate, as a model that produces many false positives may not be useful in practice.

The concept of true positive rate has been used in statistics and epidemiology for many decades, but its importance has grown with the increasing use of machine learning and artificial intelligence in various fields.

sensitivity recall hit rate

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