How dipeshvbante31/customer-churn-analysis-prediction works
Customer Churn Analytics is a Flask application that turns customer CSV data into churn predictions and retention insights. Its main workflow validates and cleans a dataset, engineers features, trains and evaluates candidate models, predicts customer risk, then serves results through dashboard pages and APIs backed by SQLite. The README also documents segmentation, explanations, revenue-at-risk, early warnings, recommendations, simulations, and CSV upload/export. Several page implementations are unsampled; those capabilities are represented at the documented application layer, without asserting unverified internal calls.
Main entry points: app.py Flask routes · train_model.py Model training · data_loader.py Data validation · prediction.py Churn prediction
Components 16
Web application
- Flask routes
app.py - Dashboard & APIs
app.py - Customer views
app.py - Dataset upload
app.py - What-if simulator
app.py
Data management
- Data validation
src/data_loader.py - SQLite records
src/database.py
Model pipeline
- Feature processing
src/feature_engineering.py - Model training
src/train_model.py - Model evaluation
src/evaluate_model.py - Churn prediction
src/prediction.py
Customer insights
- Customer segments
src/segmentation.py - Prediction explanations
src/explainability.py - Retention insights
app.py - Analytics & revenue
app.py
Other components
- Analyst
Connections 21
- Analyst → Flask routes: uses
README.md - Flask routes → Dashboard & APIs: routes requests
README.md - Flask routes → Customer views: routes requests
README.md - Flask routes → Dataset upload: routes uploads
app.py - Flask routes → What-if simulator: handles simulation
app.py - Dataset upload → Data validation: validates data
README.md - Flask routes → Data validation: loads dataset
app.py - Data validation → Model training: provides data
src/train_model.py - Model training → Feature processing: builds pipeline
src/train_model.py - Model training → Model evaluation: evaluates models
src/train_model.py - Flask routes → Model training: trains model
app.py - Flask routes → Churn prediction: predicts batch
app.py - Churn prediction → Model training: loads model
src/prediction.py - Flask routes → SQLite records: reads and writes
README.md - Dashboard & APIs → SQLite records: reads metrics
README.md - Customer views → SQLite records: reads records
README.md - Flask routes → Customer segments: builds segments
app.py - Flask routes → Prediction explanations: explains predictions
app.py - Customer views → Retention insights: shows recommendations
app.py - Dashboard & APIs → Analytics & revenue: shows analytics
app.py - What-if simulator → Churn prediction: compares predictions
app.py