Bayesian average - Wikipedia, the free encyclopedia     http://en.wikipedia.org/wiki/Bayesian_average     tags: votes rating Google Answers: Alternatives to IMDB's formula     IMDB uses this famous formula: weighted rank (WR) = (v (v+m)) R + (m (v+m)) C where: R = average for the movie (mean) = (Rating) v = number of votes for the movie = (votes) m = minimum votes required to be listed in the Top 250 (currently 1250) C = the mean vote across the whole report (currently 6.8) This formula is exceedingly useful, but I have beef with the "m" variable, because it's arbitrary. As far as I can tell, the other three variables should be enough to calculate what score a movie would have if it had a quadrillion votes. So why is this "m" nonsense thrown in, and is there any formula that avoids it?     http://answers.google.com/answers/threadview/id/507508.html     tags: imdb rating starts votes How Not To Sort By Average Rating     CORRECT SOLUTION: Score = Lower bound of Wilson score confidence interval for a Bernoulli parameter Say what: We need to balance the average rating with the uncertainty of a small number of observations. Fortunately, the math for this was worked out in 1927 by Edwin B. Wilson. What we want to ask is: Given the ratings I have, there is a 95% chance that the "real" average rating is at least what? Wilson gives the answer. For simplicity we suppose that there are only positive ratings with value 1 and negative ratings with value 0.     http://www.evanmiller.org/how-not-to-sort-by-average-rating....     tags: stats algorithm stars rating linkiblog | How to Build a Popularity Algorithm You can be P...     Many web sites allow users to casts vote on items. These visitors' votes are then often used to detect the items' "popularity" and hence rank the rated items accordingly. And when "rank" comes into play things gets tricky: * The system can have inherent deficiencies in ranking items. That is mostly because developers tend to "re-invent the wheel" and throw in their own algorithms instead of basing their calculations on well-established statistical formulae (I'll come to that in a moment, just bear with me Wink). * There will be people (i.e. spammers) trying to fool the system and try to take their submissions to top. * There will be system inefficiencies due to computational complexity. In this article, * I'll try to give examples on how to approach the problem; * describe the weakness of each particular approach; * and explain how some well-known social community sites implement their ranking algorithms.     http://blog.linkibol.com/post/How-to-Build-a-Popularity-Algo...     tags: rating votes popularity