Due to recent updates, all users are required to create an Altair One account to login to the RapidMiner community. Click the Register button to create your account using the same email that you have previously used to login to the RapidMiner community. This will ensure that any previously created content will be synced to your Altair One account. Once you login, you will be asked to provide a username that identifies you to other Community users. Email us at Community with questions.

Clustering Model Visualizer

JP_1903JP_1903 Member Posts: 1 Learner I
edited February 2020 in Help
Hi,

I used Rapidminer for the first time for clustering with kmeans. I dont have any data experience so I dont really understand the results (overview, heat map etc) from the clustering model visualizer. I just cant interpret them.

My dataset is pretty easy with just 200 customers from a mall. There were 4 columns: Gender, Age, Annual Income, Spending Score (how often a customer was buying in a mall / spendings).
I took 3 selected attributes (age, income, spending score). In the end I want to know who belongs to my target group (high income and high spendings with information about gender and age) for marketing strategy.

So what does it mean when it says:
Cluster 0:
Annual Income is on average 71,38 % smaller, Age is on average 66.21 % smaller, Spending score is on average 54.77 % larger

Cluster 1:
....

I had k= 5 clusters.

Thanks for helping me!!! :-)

Answers

  • Telcontar120Telcontar120 RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,635 Unicorn
    This is describing the elements in any given cluster compared to the overall dataset.  So it is basically a comparison of that cluster's profile vs the whole population.
    So in your example, the first cluster (Cluster 0 because java counting starts with zero) generally has younger people with lower than average incomes, but who spend more.
    Brian T.
    Lindon Ventures 
    Data Science Consulting from Certified RapidMiner Experts
Sign In or Register to comment.