March 10, 2022, 8:48 p.m. | Dhruvil Karani

Towards Data Science - Medium towardsdatascience.com

What is ROC-AUC and when not to use it

No metric is perfect.

Original Image

Understand what a metric hides and promotes.

When a measure becomes a target, it ceases to be a good measure — Goodhart’s law

When you improve a metric, you primarily improve what the metric favours. Since no metric can measure everything, chasing one blindly can be dangerous. I want to explore what this means for ROC-AUC.

The receiver operating characteristics curve or ROC curve is …

analytics auc data science machine learning roc

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote