Skip to Content
Author's profile photo Tammy Powlas

Conclusions with Confusion – or Decision Trees

Following up from Learning about Clustering Analysis with Predictive Analysis it looks like cluster 3 is the most valuable.  To validate, I look at Decision Trees in Predictive Analysis 1.14:


I set it up as trend, classification and the 4 key measures of rental price, count, revenue and margin.  I also read up about decision trees in Wikipedia

The target variable is the cluster number from the R K means analysis.  After running the analysis one of the visualizations available is the confusion matrix:


Of course to learn more about this I turn to Wikipedia to learn more about Confusion Matrix

4couldcluster2 be more valuable.png

The decision tree above shows that cluster 2 may be more valuable than cluster 3, so maybe I should target those customers.

Assigned Tags

      Be the first to leave a comment
      You must be Logged on to comment or reply to a post.