Confusion matrix
A table comparing reference classes with model predictions and counting correct and incorrect assignments.
Which confusions does the table show?
A confusion matrix compares reference classes with model predictions. Here, rows contain cases assigned under a defined business rule and columns contain the model prediction. The fictional example covers 50 service requests; the positive class is intended for technical service. The orientation and class labels must be clear, because the same numbers can otherwise be interpreted incorrectly.
Reference class | Model: technical service | Model: other request |
|---|---|---|
Technical service | 18 | 2 |
Other request | 6 | 24 |
The 18 cases at the top left are true positives. The 2 at the top right were missed, the 6 at the bottom left were incorrectly marked positive, and the 24 at the bottom right were correctly identified as other requests. The table thus separates requests that fail to reach the technical team from extra requests wrongly sent there. It can be extended to further classes. Its meaning also depends on the quality of the reference assignments and how well the selected examples cover the intended use.
Sources
Related terms
- LLM evaluationLLM evaluation tests model outputs against defined tasks and criteria. One good example does not establish overall quality.
- Supervised learningA learning method that uses inputs together with their corresponding target values or classes as training examples.
- Test data in machine learningData reserved for final assessment whose results were not used to select the model variant being assessed.
- PrecisionThe share of actually positive cases among all cases the model marks as positive.
- RecallThe share of actually positive cases that the model correctly identifies as positive.
- F1 scoreThe harmonic mean of precision and recall for the same positive class.
Your project with ASES
Describe your project to us. We will get back to you with an initial assessment.