Measuring the similarity between data sets

41 Views Asked by At

Suppose I have a data set of movie ratings:

Movie    My Rating    Critic1 rating    Critic2 rating
  a          2             2                 4
  b          4             3                 1
  c          3             4                 5 
  d          2             3                 4
  e          3             3                 5

(assume each movie is rated 1-5)

How would I calculate which critic has the most similar taste to my own movie ratings? Preferably, I would like to calculate a percentage of similarity.