This repository contains the Python code that accompanies the Customer Value Paradox article written by Daniel Wiesenfeld and published on Towards Data Science: https://towardsdatascience.com/the-customer-value-paradox-6d908612c2b4. No data is necessary as all data is generated by the code itself.
These modules use the numpy, pandas, matplotlib, and seaborn libraries. Some modules contain variables that were declared in earlier mdoules, so I suggest running them in the following order:
- simulate_receipt_dataset.py
- category_mix.py
- customer_mix.py
- buyer_vs_nonbuyer_value.py
- graph_buyer_vs_nonbuyer.py
- simulate_3_category_dataset.py
- simulate_distributions.py
- graph_distributions.py