Statistical Estimation OF CLV

Customer Lifetime Value (CLV) is a key metric for companies looking to assess their long-term profitability. It can measure how much revenue a customer can generate for a company over the course of his or her lifetime as a customer. It can also synthesize churn risk of every single customer. Thus, CLV is an indispensable tool for companies that want to maximize their return on investment and develop effective marketing and loyalty strategies. In this project, we will mainly take a look at the CLV from a statistical point of view. We will also discuss the methods for calculating CLV such as Kaplan Meier estimator.

Folder Structure

report.pdf: This is the report file, including a modifiable version on Overleaf.

The src folder contains the following files:

• notebook.ipynb: This Jupyter notebook contains the testing and analysis of real data.
• geometric.ipynb: This Jupyter notebook contains the processing of the geometric estimator.
• exponential.ipynb: This Jupyter notebook contains the processing of the exponential estimator.
• pareto.ipynb: This Jupyter notebook contains the processing of the Pareto estimator.
• functions.py: This Python file contains the developed functions.

Usage

To use the notebooks and functions in this project, you can follow these steps:

1. Clone the repository github repository or download the project files
2. Install the necessary dependencies and libraries.
3. Open notebooks (notebook.ipynb, geometric.ipynb, exponential.ipynb, pareto.ipynb) using Jupyter Notebook or JupyterLab.
4. Run the cells in the notebooks to execute the code and perform the estimations and analyses.
5. Refer to the report.pdf file for a detailed report on the project. You can find the modifiable version of the report on Overleaf using the provided link.