Metrics for imbalanced data

1. What is a good metric for imbalanced class problems?
2. Is F1 score good for imbalanced data?

What is a good metric for imbalanced class problems?

Matthew's correlation coefficient: A metric for imbalanced class problems Sometimes in data science and machine learning we encounter problems of imbalanced classes. These are problems when one class might have more instances than another.

Is F1 score good for imbalanced data?

F1 score (also known as F-measure, or balanced F-score) is a metric used to measure the performance of classification machine learning models. It is a popular metric to use for classification models as it provides robust results for both balanced and imbalanced datasets, unlike accuracy.