This is a project for Udacity's Machine-Learning Nanodegree. It uses unsupervised learning algorithms to cluster customers into groups based on purchasing data.
Concepts explored in this project:
- Unsupervised learning algorithms like K-Means Clustering and Gaussian Mixture Model Clustering
- Feature Scaling
- Dimensionality reduction using Principle Component Analysis
- Outlier identification and removal
- Silhouette scores
Relevant Classes:
To view the project, open customer_segments.html
in a web browser.