🔴 View Live Demo: https://naserr.streamlit.app/
📂 Sample Data: Need data to test? Download these example files to see the required format:
RFM Growth Engine is a powerful, interactive analytics tool designed to transform raw customer transaction data into actionable marketing insights.
Built with Python and Streamlit, this application automates the RFM (Recency, Frequency, Monetary) analysis process, allowing businesses to segment their customer base dynamically and identify "Champions", "Loyal Customers", and those "At Risk" of churning.
In traditional setups, implementing an interactive RFM dashboard with dynamic weighting usually requires:
- Data Engineering teams to build pipelines.
- BI Analysts to visualize in Tableau/PowerBI (4-8 weeks).
This Project's Approach: Adopting a "Vibecoding" (AI-First) methodology, this full-stack application was prototyped, debugged, and deployed in under 48 hours. It demonstrates how a Technical Growth Engineer can bypass technical bottlenecks to deliver immediate business value (Customer Segmentation & Churn Analysis) without waiting for heavy IT resources.
- Dynamic Weighting Strategy: Unlike static RFM tools, this engine allows users to adjust the importance of Recency, Frequency, and Monetary value (0-10 scale) to fit specific business models (e.g., High-ticket vs. FMCG).
- Smart Data Mapping: Automatically detects and suggests column mapping for any uploaded Excel file.
- Interactive Visualizations: Features dynamic Treemaps powered by Plotly to visualize segment distribution.
- Churn & Loyalty Analysis: Calculates real-time Key Performance Indicators (KPIs) such as Loyalty Rate, Churn Risk, and Average CLV.
- Privacy-Preserving: All data processing happens on-the-fly; extra columns (Emails, Phones) are preserved in the export but not stored.
- Core: Python 3.8+
- Frontend: Streamlit
- Data Processing: Pandas
- Visualization: Plotly Express
- I/O: OpenPyXL
-
Clone the repository: git clone https://github.com/naserr/rfm-growth-engine.git
cd rfm-growth-engine -
Create a virtual environment (Optional but recommended): python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate -
Install dependencies: pip install -r requirements.txt
-
Run the app: streamlit run app.py
Contributions, issues, and feature requests are welcome!
Built with ❤️ by Naser Rahmani | Technical Growth Engineer