Using Rapidminer:

1. Normalize the data and then apply an iterative kmeans clustering in RapidMiner using the XMeans operator, specifying parameters: k_min = 2, k_max = 10. How many clusters appear?
2. What would happen if the data were not normalized?
3. Compare the cluster centroid to characterize the different clusters, and try to give each cluster a label.
4. To check the stability of the clusters, remove a random 5% of the data (by taking a random sample of 95% of the records), and repeat the analysis. Does the same picture emerge?
5. Which cluster(s) would you target for marketing offers, and what types of offers would you target to customers in those cluster(s)?
6. Which cluster has a higher proportion of Churn? = LEAVE customers? Show a bar chart or a table comparing each clusters proportion of LEAVE vs. STAY. (Hint: You can analyze the Clustered Set obtained from X-Means operator to create a pivot table using Turbo Prep.)