An end-to-end Data Science project to identify high-value customer segments.
In this project, I analyzed an Online Retail dataset to segment customers based on their purchasing behavior. By applying RFM (Recency, Frequency, Monetary) analysis and K-Means Clustering, I identified 4 distinct customer groups to help drive targeted marketing strategies.
- Data Cleaning: Handled 135k+ missing values and filtered out returns/anomalies.
- RFM Engineering: Transformed raw transactions into behavioral metrics.
- Dimensionality Reduction: Used PCA to visualize 3D data in a 2D space.
- Interactive Visualization: Built a 3D scatter plot using Plotly for deep-dive analysis.
- Champions: 15% of customers; high spenders; need loyalty rewards.
- At-Risk: High recency; need re-engagement campaigns. (Include your 3D Plot screenshot here!)
- Language: Python
- Libraries: Pandas, NumPy, Scikit-Learn, Plotly, Seaborn, Matplotlib
If GitHub does not preview the video inline, click the link to open or download it.