Micro-Average Precision and Recall, F-Score:

 

·        Definition:

Ø  Micro-average precision and recall are performance metrics used in the context of multiclass classification problems, where there are multiple classes to predict.

·        Micro-Average Precision:

Ø  Micro-average precision is calculated by considering all instances and all classes collectively. It treats each instance as an individual contribution, irrespective of the class it belongs to.

Ø  Formula:

Micro-Average Precision = True Positives / (True Positives + False Positives)

 

Micro-Average Precision=Total True PositivesTotal True Positives + Total False PositivesMicro-Average Precision=Total True Positives + Total False PositivesTotal True Positives​

·        Micro-Average Recall:

Ø  Micro-average recall is also calculated by considering all instances and all classes collectively. It measures how well the model identifies all instances of each class.

Ø  Formula:

Micro-Average Recall = True Positives / (True Positives + False Negatives)

 

·        Micro-Average F-Score:

Ø  Micro-average F-score is the harmonic mean of micro-average precision and micro-average recall. It balances precision and recall in a way that considers each instance equally.

        Ø Formula:

Micro-Average F-score = 2 * (Micro-Average Precision * Micro-Average Recall) / (Micro-Average Precision + Micro-Average Recall)

Example:

Suppose we have a multiclass classification model with three classes: "A," "B," and "C." After evaluation, we have the following results:

  • Total True Positives: 80
  • Total False Positives: 10
  • Total False Negatives: 5

Now, we can calculate micro-average precision, micro-average recall, and micro-average F-score: