Do a qualitative comparison of the similarity metrics

nlesc-sherlock / cluster-analysis

2 stars 4 forks source link

Do a qualitative comparison of the similarity metrics #5

Open benvanwerkhoven opened 8 years ago

benvanwerkhoven commented 8 years ago

We currently do not know which similarity metrics is the 'best'. Perhaps it differs per dataset or per clustering algorithm that you use afterwards. What are the benefits of using one metric over the other? It would be very good if someone could look into this.

jspaaks commented 8 years ago

There is also the concept of pareto optimality, where you optimize on an arbitrary number of objectives simultaneously, while gaining (some) insight into the tradeoffs between objectivives (what does a metric measure?).