But the Wilson score is not idea. It does not take into account the number of page views. it also does not directly take into account that people are more likely to up vote than down vote. Without evidence, I think down votes should be multiplied by 5.
I am starting to use a ratio of (upVotes - downVotes)/viewCount. it is already in production on my cython widget. Next, I need to figure out the statistically correct version of that algorithm. (It has been a while since I studied statistics at MIT) Any help would be appreciated.
If you like this website, please upvote my Awesome Python pull request.