ARI takes values between -1 and 1. When I check the clustering result i got ARI = 0.21. What does it mean?. What is good ARI value?
can you recommend a good resource on ARI?
Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. It only takes a minute to sign up.Sign up to join this community
Depends on your data set.
But in general, 0.20 is really bad.
Just remember that 0 is putting everything in random buckets.
So 0.20 is a result quite close to randomness.
And don't forget that these indexes often cannot be applied on real data. If you have labels, don't use clustering. For ARI you need to know the ground truth. But then you are probably comparing result A with result B for benchmarking, and then you probably are more interested in whether A or B is "better" as in 'more similar'.
The Adjusted Rand Index is used to measure the similarity of datapoints presents in the clusters i.e., how similar the instances that are present in the cluster. So, this measure should be high as possible else we can assume that the datapoints are randomly assigned in the clusters.