Hacker News new | past | comments | ask | show | jobs | submit login

Accuracy is known to be a unreliable metric to measure the quality of a test (classifier). One paradox is that tests of higher accuracy might have less predictive power than the one with lower accuracy.

http://en.wikipedia.org/wiki/Accuracy_paradox




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: