# 5 star ratings. Bayesian or Weighted average?

I am building a website which has 5 star ratings to rate items.

These ratings unlike the normal ones are of unequal weights. i.e.

1 star: -5,
2 stars: 10,
3 stars: 20,
4 stars: 30,
5 stars: 50,


Every time a user rates I am planning to calculate the average and show it back to the user.

To do this averaging I was thinking of implementing weighted averages or Bayesian average.

Which approach do you think is the best? Are there other approaches I should be looking into?

-
Here's another approach you could look into: How Not To Sort By Average Rating by Evan Miller – Rahul Aug 16 '11 at 15:36
Questions like this don't have an objective answer. It all depends on what you want your rating system to do. – Qiaochu Yuan Aug 16 '11 at 15:37
@Rahul Evan's post is specifically for rating systems without a limit. i.e. a voting system – Cherian Aug 16 '11 at 15:42

The basic (weighted) average is really just a special case of the Bayesian average with $C = 0$. There are other special cases, such as the rule of succession, which correspond to different priors. More generally, these are all forms of additive smoothing.