This is one of my most popular article (project) on Medium. In this project, I want to know how many groups that exist from the collection of customers, and also how the characteristics for each group differs one with another. I implemented this using Python. For details, you can read my article here (https://towardsdatascience.com/customer-segmentation-in-python-9c15acf6f945)
In summary, the process were like this:
- Importing data
- Explore the data
- Generate the Recency, Frequency, and Monetary (RFM) features from the dataset
- Preprocess the data
- Do clustering using K-Means
- Analyze the clusters characteristics using charts