Ranking Images using a 5-Star Ratings System (Bayesian Statistics?)

[Djeep]

I run a photo contest that uses a 5-star rating system which ranks the images according to their average rating. However, I would like to factor in the total number of votes a photo receives to get a more accurate ranking. For example, I do not want an image with one 5-star vote (Avg rating: 5) getting ranked above an image with ten 5-star votes and one 4-star vote (Avg rating: 4.9).

If I have the following variables, what formula should I use to achieve the type of ranking desired? Do I need to factor in anything else? There are approximately 350 images to rank.

R: Average rating of image
v: Total Votes of image
C: Average rating of ALL images

I am just looking for the most basic solution that would be a step better than simply using a straight average. It doesn't have to get any more detailed than factoring in the total number of votes each item receives. Thank you!

 

[Valkarie]

I would suggest using Weighted Average Rating (WAR) for a more accurate ranking. The formula for WAR is: WAR = (R * v + C * n)/(v + n)Where R = Average rating of image, v = Total Votes of image, C = Average rating of ALL images, and n = total number of votes from all images.The Weighted Average Rating takes into account both the average rating and the total number of votes. This means that an image with one 5-star vote (Avg rating: 5) will be ranked lower than an image with ten 5-star votes and one 4-star vote (Avg rating: 4.9), as the image with more votes will have a higher WAR value.