This project is an end-to-end Customer Intelligence System that transforms raw transaction data into actionable business decisions.
It combines:
- RFM segmentation
- Customer clustering
- CLV modeling
- Decision engine (Upsell / Retain / Re-engage)
- Revenue impact simulation
👉 Goal: Identify high-value customers, detect churn risk, and simulate strategies to maximize revenue.
Most businesses struggle to answer:
- Who are our most valuable customers?
- Which customers are at risk of churn?
- How much revenue is at risk?
- What action should we take?
- What is the financial impact of retention strategies?
- No clear visibility into customer segments
- Revenue loss identified after it happens
- No prioritization of high-value customers
- Marketing spend is not optimized
- Decisions based on assumptions, not data
- Customers segmented using RFM + clustering
- At-risk customers identified proactively
- High-value customers prioritized using CLV
- Clear strategy: Upsell / Retain / Re-engage
- Revenue impact simulated before decisions
- Identified ₹8.9L+ revenue at risk
- Estimated ₹2.6L+ recoverable revenue (30% retention scenario)
- Enabled targeted retention strategy instead of generic campaigns
👉 This shifts the business from: Reactive reporting → Proactive decision-making
- Identify high-value customers
- Detect churn risk early
- Prioritize retention vs upsell
- Simulate revenue recovery
- Support business decision-making
- Recency, Frequency, Monetary scoring
- Behavioral customer grouping
- Segment customers into meaningful groups
- Identify high-value and at-risk users
- Estimate customer value using behavioral data
- Prioritize high-value users
Automatic action assignment:
- Upsell → High-value active customers
- Retain → Medium-risk customers
- Re-engage → At-risk customers
- Nurture → Low-value customers
- Calculates revenue at risk
- Estimates recoverable revenue
Interactive dashboard to answer:
“If we improve retention by X%, how much revenue can we recover?”
- Total Customers, Revenue, Orders
- Country-level distribution
- Business performance snapshot
- RFM clustering
- Customer behavior vs value analysis
- Strategy allocation
- Revenue contribution by segment
- CLV distribution
- Revenue leakage identification
- Retention rate slider (What-if analysis)
- Revenue at risk vs recovery
- At-risk customer targeting
- Business decision insights
- Python → Data processing
- Pandas / NumPy → Transformation
- Scikit-learn → Clustering
- MySQL → Data storage
- Power BI → Visualization & simulation
customer-intelligence-platform/
│
├── data/
│ └── raw_transactions.csv
│
├── src/
│ ├── ingestion.py
│ ├── transform.py
│ ├── rfm.py
│ ├── clustering.py
│ ├── clv_model.py
│ ├── decision_engine.py
│
├── sql/
│ └── schema.sql
│
├── app/
│ └── streamlit_app.py
│
├── powerbi/
│ └── dashboard.pbix
│
├── assets/
│ ├── page1.png
│ ├── page2.png
│ ├── page3.png
│ ├── page4.png
│
├── main.py
├── requirements.txt
└── README.md
git clone https://github.com/<your-username>/customer-intelligence-platform.git
cd customer-intelligence-platform
pip install -r requirements.txt
python main.py
- Load output dataset into Power BI
- Open
dashboard.pbix
- A small percentage of customers drive the majority of revenue
- Significant revenue lies in at-risk segments
- Retention improvements directly impact revenue recovery
✔ Identifies revenue leakage ✔ Prioritizes high-value customers ✔ Enables proactive retention strategies ✔ Simulates real-world business impact
This is not just a dashboard.
It is a decision intelligence system that:
- Connects data → business strategy
- Moves from reporting → prediction
- Enables simulation → decision-making
Jagadeeswari S Data Analyst | SQL | Power BI | Python
If you found this useful, consider giving it a ⭐