Back to Developer Roadmap

False Positive Vs Negative

src/data/question-groups/data-science/content/false-positive-vs-negative.md

4.0729 B
Original Source

False Positive Rate (FPR) is the proportion of actual negatives that are incorrectly identified to be true. False Negative Rate is the proportion of actual positives that are incorrectly identified as negatives.

In a fraud detection scenario, both of these have damaging consequences:

False Positive Rate (FPR): If a model has a high false positive rate, it means the system flags many legitimate transactions as fraudulent. This will lead to customer frustration, as their transactions will be flagged regularly, and they could leave.

False Negative Rate (FNR): If a model has a high false negative rate, it means many fraudulent transactions are not detected, which could lead to significant financial business loss.