Unveiling Hidden Patterns in Credit Card Usage: A Clustering Approach
This project aims to perform credit card customer segmentation using K-means clustering analysis on customer transaction data. By segmenting customers into four distinct groups based on their spending behavior and demographics, financial institutions can tailor marketing strategies, improve customer satisfaction, and optimize business operations.
The dataset used in this project (BankChurners.csv
) contains information about credit card transactions, including transaction amount, transaction date, customer demographics, and other relevant features.
The feature set used in this project is as follows:
assets/
: Directory to store model images and figures.data/
: Directory to store dataset(s).notebooks/
: Directory to store Google Colab notebook for data preprocessing, exploratory data analysis (EDA), and clustering analysis.requirements.txt
: File containing project dependencies.
- Clone the repository:
git clone https://github.com/HassanMahmoodKhan/Credit-Card-Customer-Segmentation-A-Clustering-Approach.git
- Navigate to the project directory:
cd Credit-Card-Customer-Segmentation-A-Clustering-Approach
- Install dependencies:
pip install -r requirements.txt
- Explore the Google Colab notebook in the
notebooks/
directory for data preprocessing, EDA, and clustering analysis. - Refer to the project figures and visuals in the
assets/
directory for additional information.
zhyli. (2020). Prediction of Churning Credit Card Customers [Data set]. Zenodo. https://doi.org/10.5281/zenodo.4322342
This project is licensed under the Apache 2.0 License - see the LICENSE file for details.