Skip to content

If macro F1 is smaller than 0.5, does it mean it is even worse than a random classifier? #3

Open
Open
If macro F1 is smaller than 0.5, does it mean it is even worse than a random classifier?#3

Description

@JunwenBai
JunwenBai
opened on Sep 29, 2019

Given a random predictor, it is expected to obtain 0.5 F1-score, right? The macro-F1 is even smaller than 0.4. How to explain this?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions