A false positive occurs when the classifier predicts one category but the true label is different. For example, classifying a return as 'defective' when the customer actually 'changed their mind.' False positives create misleading analytics, potentially causing merchants to redesign products or adjust policies based on inaccurate data. Monitoring false positive rates helps maintain classification reliability.
← Glossary
False Positive
When the AI incorrectly assigns a return reason that doesn't match the actual reason.
Related terms
- False Negative — When the AI fails to identify the correct return reason and assigns an incorrect one.
- Confidence Score — A number between 0 and 1 indicating how certain the AI model is about its classification decision.
- Model Accuracy — The percentage of classifications the AI model gets correct across all categories.
- Threshold — The minimum confidence score required for the AI to auto-assign a classification versus flagging for human review.