This project applies unsupervised machine learning techniques to segment customers based on their purchasing behavior. Using clustering algorithms such as K-Means, the goal is to identify meaningful customer groups to drive targeted marketing, loyalty initiatives, and business decision-making.
The analysis provides clear insights into customer segments like high-value loyal customers, new or low-engagement customers, and those at risk of churn — allowing businesses to take data-driven actions.
Dataset Source: Online Retail II - UCI Machine Learning Repository
- Understand customer purchasing patterns through data exploration
- Apply clustering to group customers with similar behaviors
- Interpret clusters and recommend actions for business strategy
- Visualize the segmentation results for better clarity
main.ipynb: Main Jupyter Notebook containing data preprocessing, clustering, and insight generation.README.md: Project description and insights summary.- (Optional)
requirements.txt: Python dependencies (if applicable).
-
Cluster 0 (Red) – "Retain": High-value customers who purchase regularly but not recently. Focus on maintaining loyalty through engagement and offers.
-
Cluster 1 (Green) – "Re-Engage": Infrequent, low-value customers who haven't purchased in a while. Use targeted marketing to win them back.
-
Cluster 2 (Blue) – "Nurture": Recently active but low-value customers, possibly new. Build relationships and encourage more frequent purchases.
-
Cluster 3 (Yellow) – "Reward": High-value, frequent buyers. Your most loyal segment — reward them with exclusives and recognition.
- Python (Pandas, NumPy, Matplotlib, Seaborn, Scikit-learn)
- Jupyter Notebook
- Machine Learning: K-Means Clustering
- Data Visualization
- Clone the repository
git clone https://github.com/AhmedQassemDev2004/Online_Retail_Customer_Segmentation.git cd Online_Retail_Customer_Segmentation