Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Perhaps you can extend the F1-score[1] to be an F1,w-score that weights errors based on some measure of distance from correctness.

[1]http://en.wikipedia.org/wiki/F1_score



Sounds like a good idea. Finding that distance heuristic will be a challenge though!




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

Search: