Skip to content

marcolomele/churn-bcgx

Repository files navigation

Churn Prediction – BCG X Data Science Competition

This repository contains the solution developed for a Data Science competition judged by BCG X. The objective was to isolate key drivers of churn and build a predictive model to identify customers at risk of churn.

📂 Repository Structure

churn_bcgx/
├── data/             # Raw and processed datasets
├── inference/        # Scripts for model inference
├── main/             # Main execution scripts
├── modelling/        # Model training, evaluation, and prediction code
├── supplementary/    # Additional resources and documentation
├── .gitignore        # Git ignore file
└── LICENSE           # Project license (Apache 2.0)
  • data/: Contains raw and processed datasets used for training and evaluation.
  • inference/: Scripts and utilities for running model inference on new data.
  • main/: Main scripts to execute the pipeline or key project steps.
  • modelling/: Code for model training, validation, and prediction.
  • supplementary/: Additional resources, documentation, or supporting materials.

🚀 Getting Started

  1. Clone the repository:

    git clone https://github.com/marcolomele/churn_bcgx.git
    cd churn_bcgx
  2. Set up a virtual environment and install dependencies using requirements.txt.

  3. Explore the main/ directory for entry-point scripts to reproduce results or run the pipeline.

💽 Data

  • The data/ directory contains all datasets used in the project.

🧪 Modeling

  • All model development, training, and evaluation scripts are located in the modelling/ directory.

🔭 Inference

  • The inference/ directory contains notebooks on inferring churn drivers via data analysis.

📚 Supplementary Materials

  • Additional work using Small Language Model to generate emotional involvement of customers is in the supplementary/ directory.

📊 Results

  • Identified multiple churn drivers that align with business intuition. The final model achieved strong performance in predicting customer churn.
  • See Churn Modelling Presentation.pdf for an overview of our methods and the results.
  • See Churn Modelling Report.pdf for an in-depth explanation of our methods and the results.

🤝 Contributors

🔑 License

This project is licensed under the Apache-2.0 License. See the LICENSE file for details.

About

Solution for a customer churn prediction competition judged by BCG X. Includes data processing, model training, evaluation, and inference scripts. Status: completed.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors