https://www.analyticsvidhya.com/blog/2021/06/confusion-matrix-for-multi-class-classification/
You have different options when calculating quality metrics in multi-class classification.
1.Calculating precision and recall by class is useful when you want to evaluate the performance of a classifier for a specific class of interest or when dealing with imbalanced classes, but it can result in a large number of performance metrics.
When you have a large number of classes or want a more concise summary of overall performance, using macro or micro averages can be a better option.
2.Macro-averaging shows average performance across classes, treating each class as equally important.
3.Micro-averaging gives equal weight to every instance and shows average performance across all predictions. In the case of multi-class classification, micro-averaged precision, recall, and accuracy are the same.
4.You might also consider using weighted averaging based on the proportion each class takes in the dataset. This approach is useful if you have an imbalanced dataset but want to assign larger importance to classes with more examples.
Recap
https://www.evidentlyai.com/classification-metrics/multi-class-metrics
