This project is the last part of the machine learning Udacity course where I have to implement an unsupervised algorithm to identify general population segments for a company to prepare a marketing campaign.
The project consists of three parts:
- Processing the data (general population) to be used (this is: cleaning the data, encoding categorical and mixed-type features and dropping unneeded data)
- Scaling and imputing missing values prior to analyze the components using PCA and find the clusters to group the data
- Apply the models to the customer data and find interesting population segments