Customer-Segmentation

This is a Udacity machine learning nanodegree project deliverable, please use in accordance with Udacity honor code.

Project Goals

1. Implement unsupervised techniques to see what sort of patterns exist among existing customers, and what exactly makes them different.
2. Review unstructured data to understand the patterns and natural categories that the data fits into.
3. Use multiple algorithms and both empirically and theoretically compare and contrast their results.
4. Make predictions about the natural categories of multiple types in a dataset, then check these predictions against the result of unsupervised analysis.

Software and Libraries

The following SW was used in the first part of the project:

• Python 2.7
• NumPy
• scikit-learn
• pandas
• matplotlib
• iPython Notebook

In the last part of this project, R was used as an EDA tool:

• R 3.2.3
• ggplot
• ggbiplot

Data Set Source

The dataset refers to clients of a wholesale distributor. It includes the annual spending in monetary units (m.u.) on diverse product categories. It is part of a larger database published with the following paper:

Abreu, N. (2011). Analise do perfil do cliente Recheio e desenvolvimento de um sistema promocional. Mestrado em Marketing, ISCTE-IUL, Lisbon.

Final Report and IPython Notebook

Final report and IPython notebook are included in this repository. IPython notebook is straightforward to use, please refer to http://cs231n.github.io/ipython-tutorial/ for a quick tutorial.