I am following along with the new SAP Press book Predictive Analysis which helps give some background. I also read the wikipedia link on K-Means clustering.
I have a sample CSV file of rentals, go to the Predict tab, and select the R-K Means algorithm under Clustering.
Above shows I am selecting 5 clusters, and all features in column selection.
Then I select "Run" to run the clustering analysis.
In the results screen I can see various cluster representations. Above shows a bar chart of clusters.
In reading the book, the "thicker the density" the closer the clusters in the above chart.
Above is the parallel coordinates chart.
Are cluster 3 customers the most valuable ones, according to this chart? To be continued...
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.
User | Count |
---|---|
9 | |
9 | |
7 | |
6 | |
5 | |
4 | |
4 | |
3 | |
3 | |
3 |