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

When you reduce a person down to a scalar, you're inevitably losing most of the signal in the different variables which go into that calculation. I am extremely skeptical that it's possible to come up with a model which makes that scalar useful to a hiring manager across a pool of candidates, even if you're some kind of data-science messiah. My .02 is that applicant scoring this way is inherently broken from a signal to noise perspective. (In fact, I bet if you just took GPA as the ranking metric, its performance would be superior as it's more competitive/harder to game, despite GPA being widely acknowledged as a subpar hiring metric - at least in my experience.)

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