Find more posts tagged with
Sort by:
1 - 5 of
51
Hi again,
I guess the Silhoutte performance comes from a 3rd party extension, so I can't say much about it. But wikipedia has an entry about it:
https://en.wikipedia.org/wiki/Silhouette_(clustering)
In short it messaures how similar an Example is to the rest of the cluster. The value is normed between -1 and +1 and a high value indicates a higher similarity.
The Davies–Bouldin criterion is also quite good explained in wikipedia:
https://en.wikipedia.org/wiki/Davies%E2%80%93Bouldin_index
The idea is to maximise the inter-cluster distance (the different between the different clusters) and minimize inter-cluster distances (the points within each cluster should be close together). Here a lower index is better.
Best,
David
Hi,
finding optimal settings for clustering is indeed a bit tricky.
But RapidMiner offers performance measures for clustering or segmentation tasks.
In the Operator list under Validation -> Segmentation you'll find the corresponding Operators.
If you have a subset of your data, where you exactly know into which cluster each example belongs, you can also try to set the cluster Attribute as a prediction and optimize the classification performance instead.
Best,
David