You are working on a binary classification ML algorithm that detects whether an image of a classified scanned document contains a company's logo. In the dataset, 96% of examples don't have the logo, s

The correct answer is A. F-score where recall is weighed more than precision. Even a model which always says that don't have the logo will have a good precision because is the most common. What we need is improve recall.

Submitted by mike_84· Apr 18, 2026Problem framing

Question

You are working on a binary classification ML algorithm that detects whether an image of a classified scanned document contains a company's logo. In the dataset, 96% of examples don't have the logo, so the dataset is very skewed. Which metrics would give you the most confidence in your model?

Options

AF-score where recall is weighed more than precision
BRMSE
CF1 score
DF-score where precision is weighed more than recall

How the community answered

(37 responses)

A
65% (24)
B
22% (8)
C
11% (4)
D
3% (1)

Explanation

Even a model which always says that don't have the logo will have a good precision because is the most common. What we need is improve recall.

Topics

#Imbalanced datasets#Classification metrics#F-score#Recall

Community Discussion

No community discussion yet for this question.

Full PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice