In this class I cover the basics of clustering models to perform tasks like customer segmentation. First, I give an overview about what clustering is and why we would use it. I introduce several use cases where these methods could be used. I then cover the basics of the K-Means method and give an example of an insurance customer segmentation use case. This example uses the Python package scikit-learn.

---

Data Available Here and Code Available Here

Suggested Reading:

• The Unsupervised Learning Workshop by Jones, Kruger, and Johnston, Chapter 1
• Hierarchical clustering is included in slides, but I did not have time to cover it in class. To learn more about this topic read Chapter 2 of book listed in the first bullet.