How ravirathodnenavath/bank-customer-churn-prediction works
This repository is a customer-churn analysis notebook. Its documented workflow loads bank customer data, cleans and engineers features, handles class imbalance and outliers, and scales features; it also explores churn patterns, trains and tunes several classifiers, then evaluates them. The README identifies Random Forest as the best-performing final model. The tree contains only the notebook, and no source excerpts were provided, so component paths point to main.ipynb and relationships are limited to those documented in the README.
Main entry points: main.ipynb Preprocessing
Components 8
Data Preparation
- Preprocessing
main.ipynb
Churn Analysis
- Exploratory Analysis
main.ipynb - Churn Findings
main.ipynb
Modeling and Evaluation
- Model Training
main.ipynb - Hyperparameter Tuning
main.ipynb - Model Evaluation
main.ipynb
Other components
- Analyst
- Customer Data
Connections 8
- Analyst → Customer Data: provides data
README.md - Customer Data → Preprocessing: loads and cleans
README.md - Preprocessing → Exploratory Analysis: supports exploration
README.md - Preprocessing → Model Training: provides features
README.md - Exploratory Analysis → Churn Findings: identifies patterns
README.md - Model Training → Hyperparameter Tuning: tunes models
README.md - Hyperparameter Tuning → Model Evaluation: evaluates models
README.md - Model Evaluation → Churn Findings: reports performance
README.md