Segmentation Machine Learning Models

K Means Clustering Algorithm

Model - Customer Segmentation Using K-Means Clustering. Determine number of Optimal Clusters Using The Elbow Method.

Data Source - Mall Customer Segmentation Data for competition held on Kaggle

Takeaways:

Identified 5 customer clusters/segments that can be aid the sales & marketing teams on strategy accordingly.
Range of spending score is more than the annual income range
Female population clearly outweigh their male counterpart
26–35 age group outweighs every other age group
Majority of the customers have spending score in the range 41–60.
Majority of the customers have annual income in the range 60000 and 90000

Model - Customer Segmentation Using Recency/Monetary Matrix

Data Source - Global Superstore data by Tableau

Takeaways:

There are few customers in the “Disengaged” bucket and they have an average revenue higher than the “Star” bucket. Action is to coantact the customers and activate them. Engage
The average last order from the “Light” bucket is very old (> 1 yr vs. 60-70 days for ‘engaged’ customers). Launch a simple reactivation campaign

Name		Name	Last commit message	Last commit date
Latest commit History 7 Commits
data		data
.gitattributes		.gitattributes
2x2matrix.png		2x2matrix.png
K Means Clustering Algorithm.ipynb		K Means Clustering Algorithm.ipynb
README.md		README.md
RFM - Simple Customer Segmentation.ipynb		RFM - Simple Customer Segmentation.ipynb