[LUCENE-7305] Use macro average in confusion matrix metrics to normalize imbalanced classes

• Type: Improvement
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 6.1
• Component/s: modules/classification
• Lucene Fields: New
• Assignee: Tommaso Teofili
• Reporter: Tommaso Teofili
• Created: 26/May/16 14:13
• Updated: 28/Aug/22 14:58
• Resolved: 26/May/16 14:38

Description

ConfusionMatrix multi class measures should be based on macro average to avoid bias (for the good or the bad) from imbalanced classes.