← Glossary

Multi-class Classification

A classification task where each input can be assigned one of three or more possible categories.

Multi-class classification means the model chooses from more than two possible categories. Instead of just 'defective' or 'not defective,' multi-class models assign reasons like 'damaged product,' 'wrong item,' 'size issue,' 'not as described,' or 'changed mind.' Most return reason classification tasks are multi-class problems requiring models that can distinguish between dozens of nuanced categories.

Related terms

  • AI Classifier — A machine learning model that automatically categorizes inputs—like return reasons or customer feedback—into predefined groups.
  • Return Reason Classification — The process of categorizing why customers return products using AI to analyze descriptions, images, or structured data.
  • Training Data — The labeled examples used to teach an AI model how to categorize returns correctly.
  • Model Accuracy — The percentage of classifications the AI model gets correct across all categories.

Want to see this in practice?

Start a trial