Data Science
GitHub RepositoryMall Customer Segmentation
Customer segments explored through reproducible analysis, comparative reports, and an interactive dashboard.
Summary
The project explores customer groups with K-Means clustering and PCA while keeping the analysis reproducible across Python and R workflows. Generated reports capture the analytical output, and a FastAPI and React interface provides a practical way to run and inspect the segmentation process.
From customer data to interpretable segments
Dataset
Customer attributes enter the workflow
Preparation
Python and R clean and scale the data
Clustering
K-Means and PCA expose customer groups
Reports
Generated outputs preserve each analysis
Dashboard
The web interface runs and presents results
What the system handled
Combines clustering, PCA, report generation, and a web dashboard for reproducible analysis.
Technology
Stack
Areas
Conclusions
- Using the same analytical goal across Python and R made the workflow easier to compare and reduced dependence on a single report format.
- PCA visualized the clusters, and the original customer attributes supplied the meaning of each segment.
- The dashboard makes the analysis repeatable, while the generated reports preserve a static record of the parameters and results used for interpretation.
Want to inspect the implementation?
The repository contains the source, setup notes, and development history.